Daily Papers

Excellence in a wide variety of medical applications poses considerable challenges for AI, requiring advanced reasoning, access to up-to-date medical knowledge and understanding of complex multimodal data. Gemini models, with strong general capabilities in multimodal and long-context reasoning, offer exciting possibilities in medicine. Building on these core strengths of Gemini, we introduce Med-Gemini, a family of highly capable multimodal models that are specialized in medicine with the ability to seamlessly use web search, and that can be efficiently tailored to novel modalities using custom encoders. We evaluate Med-Gemini on 14 medical benchmarks, establishing new state-of-the-art (SoTA) performance on 10 of them, and surpass the GPT-4 model family on every benchmark where a direct comparison is viable, often by a wide margin. On the popular MedQA (USMLE) benchmark, our best-performing Med-Gemini model achieves SoTA performance of 91.1% accuracy, using a novel uncertainty-guided search strategy. On 7 multimodal benchmarks including NEJM Image Challenges and MMMU (health & medicine), Med-Gemini improves over GPT-4V by an average relative margin of 44.5%. We demonstrate the effectiveness of Med-Gemini's long-context capabilities through SoTA performance on a needle-in-a-haystack retrieval task from long de-identified health records and medical video question answering, surpassing prior bespoke methods using only in-context learning. Finally, Med-Gemini's performance suggests real-world utility by surpassing human experts on tasks such as medical text summarization, alongside demonstrations of promising potential for multimodal medical dialogue, medical research and education. Taken together, our results offer compelling evidence for Med-Gemini's potential, although further rigorous evaluation will be crucial before real-world deployment in this safety-critical ___domain.

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of Gemini models in cross-modal reasoning and language understanding will enable a wide variety of use cases and we discuss our approach toward deploying them responsibly to users.

This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate strong performance across academic benchmarks for language understanding, reasoning, and safety. We release two sizes of models (2 billion and 7 billion parameters), and provide both pretrained and fine-tuned checkpoints. Gemma outperforms similarly sized open models on 11 out of 18 text-based tasks, and we present comprehensive evaluations of safety and responsibility aspects of the models, alongside a detailed description of model development. We believe the responsible release of LLMs is critical for improving the safety of frontier models, and for enabling the next wave of LLM innovations.

The recently released Google Gemini class of models are the first to comprehensively report results that rival the OpenAI GPT series across a wide variety of tasks. In this paper, we do an in-depth exploration of Gemini's language abilities, making two contributions. First, we provide a third-party, objective comparison of the abilities of the OpenAI GPT and Google Gemini models with reproducible code and fully transparent results. Second, we take a closer look at the results, identifying areas where one of the two model classes excels. We perform this analysis over 10 datasets testing a variety of language abilities, including reasoning, answering knowledge-based questions, solving math problems, translating between languages, generating code, and acting as instruction-following agents. From this analysis, we find that Gemini Pro achieves accuracy that is close but slightly inferior to the corresponding GPT 3.5 Turbo on all tasks that we benchmarked. We further provide explanations for some of this under-performance, including failures in mathematical reasoning with many digits, sensitivity to multiple-choice answer ordering, aggressive content filtering, and others. We also identify areas where Gemini demonstrates comparably high performance, including generation into non-English languages, and handling longer and more complex reasoning chains. Code and data for reproduction can be found at https://github.com/neulab/gemini-benchmark

Today's generative AI systems are tuned to present information by default rather than engage users in service of learning as a human tutor would. To address the wide range of potential education use cases for these systems, we reframe the challenge of injecting pedagogical behavior as one of pedagogical instruction following, where training and evaluation examples include system-level instructions describing the specific pedagogy attributes present or desired in subsequent model turns. This framing avoids committing our models to any particular definition of pedagogy, and instead allows teachers or developers to specify desired model behavior. It also clears a path to improving Gemini models for learning -- by enabling the addition of our pedagogical data to post-training mixtures -- alongside their rapidly expanding set of capabilities. Both represent important changes from our initial tech report. We show how training with pedagogical instruction following produces a LearnLM model (available on Google AI Studio) that is preferred substantially by expert raters across a diverse set of learning scenarios, with average preference strengths of 31\% over GPT-4o, 11\% over Claude 3.5, and 13\% over the Gemini 1.5 Pro model LearnLM was based on.

We propose an agent architecture that automates parts of the common reinforcement learning experiment workflow, to enable automated mastery of control domains for embodied agents. To do so, it leverages a VLM to perform some of the capabilities normally required of a human experimenter, including the monitoring and analysis of experiment progress, the proposition of new tasks based on past successes and failures of the agent, decomposing tasks into a sequence of subtasks (skills), and retrieval of the skill to execute - enabling our system to build automated curricula for learning. We believe this is one of the first proposals for a system that leverages a VLM throughout the full experiment cycle of reinforcement learning. We provide a first prototype of this system, and examine the feasibility of current models and techniques for the desired level of automation. For this, we use a standard Gemini model, without additional fine-tuning, to provide a curriculum of skills to a language-conditioned Actor-Critic algorithm, in order to steer data collection so as to aid learning new skills. Data collected in this way is shown to be useful for learning and iteratively improving control policies in a robotics ___domain. Additional examination of the ability of the system to build a growing library of skills, and to judge the progress of the training of those skills, also shows promising results, suggesting that the proposed architecture provides a potential recipe for fully automated mastery of tasks and domains for embodied agents.

Vision-Language Models (VLMs), such as recent Qwen and Gemini models, are positioned as general-purpose AI systems capable of reasoning across domains. Yet their capabilities in scientific imaging, especially on unfamiliar and potentially previously unseen data distributions, remain poorly understood. In this work, we assess whether generic VLMs, presumed to lack exposure to astronomical corpora, can perform morphology-based classification of radio galaxies using the MiraBest FR-I/FR-II dataset. We explore prompting strategies using natural language and schematic diagrams, and, to the best of our knowledge, we are the first to introduce visual in-context examples within prompts in astronomy. Additionally, we evaluate lightweight supervised adaptation via LoRA fine-tuning. Our findings reveal three trends: (i) even prompt-based approaches can achieve good performance, suggesting that VLMs encode useful priors for unfamiliar scientific domains; (ii) however, outputs are highly unstable, i.e. varying sharply with superficial prompt changes such as layout, ordering, or decoding temperature, even when semantic content is held constant; and (iii) with just 15M trainable parameters and no astronomy-specific pretraining, fine-tuned Qwen-VL achieves near state-of-the-art performance (3% Error rate), rivaling ___domain-specific models. These results suggest that the apparent "reasoning" of VLMs often reflects prompt sensitivity rather than genuine inference, raising caution for their use in scientific domains. At the same time, with minimal adaptation, generic VLMs can rival specialized models, offering a promising but fragile tool for scientific discovery.

Large Language Models (LLMs) have attained human-level accuracy on medical question-answer (QA) benchmarks. However, their limitations in navigating open-ended clinical scenarios have recently been shown, raising concerns about the robustness and generalizability of LLM reasoning across diverse, real-world medical tasks. To probe potential LLM failure modes in clinical problem-solving, we present the medical abstraction and reasoning corpus (M-ARC). M-ARC assesses clinical reasoning through scenarios designed to exploit the Einstellung effect -- the fixation of thought arising from prior experience, targeting LLM inductive biases toward inflexible pattern matching from their training data rather than engaging in flexible reasoning. We find that LLMs, including current state-of-the-art o1 and Gemini models, perform poorly compared to physicians on M-ARC, often demonstrating lack of commonsense medical reasoning and a propensity to hallucinate. In addition, uncertainty estimation analyses indicate that LLMs exhibit overconfidence in their answers, despite their limited accuracy. The failure modes revealed by M-ARC in LLM medical reasoning underscore the need to exercise caution when deploying these models in clinical settings.

Gemini is increasingly used to perform tasks on behalf of users, where function-calling and tool-use capabilities enable the model to access user data. Some tools, however, require access to untrusted data introducing risk. Adversaries can embed malicious instructions in untrusted data which cause the model to deviate from the user's expectations and mishandle their data or permissions. In this report, we set out Google DeepMind's approach to evaluating the adversarial robustness of Gemini models and describe the main lessons learned from the process. We test how Gemini performs against a sophisticated adversary through an adversarial evaluation framework, which deploys a suite of adaptive attack techniques to run continuously against past, current, and future versions of Gemini. We describe how these ongoing evaluations directly help make Gemini more resilient against manipulation.

In health, most large language model (LLM) research has focused on clinical tasks. However, mobile and wearable devices, which are rarely integrated into such tasks, provide rich, longitudinal data for personal health monitoring. Here we present Personal Health Large Language Model (PH-LLM), fine-tuned from Gemini for understanding and reasoning over numerical time-series personal health data. We created and curated three datasets that test 1) production of personalized insights and recommendations from sleep patterns, physical activity, and physiological responses, 2) expert ___domain knowledge, and 3) prediction of self-reported sleep outcomes. For the first task we designed 857 case studies in collaboration with ___domain experts to assess real-world scenarios in sleep and fitness. Through comprehensive evaluation of ___domain-specific rubrics, we observed that Gemini Ultra 1.0 and PH-LLM are not statistically different from expert performance in fitness and, while experts remain superior for sleep, fine-tuning PH-LLM provided significant improvements in using relevant ___domain knowledge and personalizing information for sleep insights. We evaluated PH-LLM ___domain knowledge using multiple choice sleep medicine and fitness examinations. PH-LLM achieved 79% on sleep and 88% on fitness, exceeding average scores from a sample of human experts. Finally, we trained PH-LLM to predict self-reported sleep quality outcomes from textual and multimodal encoding representations of wearable data, and demonstrate that multimodal encoding is required to match performance of specialized discriminative models. Although further development and evaluation are necessary in the safety-critical personal health ___domain, these results demonstrate both the broad knowledge and capabilities of Gemini models and the benefit of contextualizing physiological data for personal health applications as done with PH-LLM.

Large language models (LLMs) have significantly advanced natural language understanding and demonstrated strong problem-solving abilities. Despite these successes, most LLMs still struggle with solving mathematical problems due to the intricate reasoning required. This paper investigates the mathematical problem-solving capabilities of LLMs using the newly developed "MathOdyssey" dataset. The dataset includes diverse mathematical problems at high school and university levels, created by experts from notable institutions to rigorously test LLMs in advanced problem-solving scenarios and cover a wider range of subject areas. By providing the MathOdyssey dataset as a resource to the AI community, we aim to contribute to the understanding and improvement of AI capabilities in complex mathematical problem-solving. We conduct benchmarking on open-source models, such as Llama-3 and DBRX-Instruct, and closed-source models from the GPT series and Gemini models. Our results indicate that while LLMs perform well on routine and moderately difficult tasks, they face significant challenges with Olympiad-level problems and complex university-level questions. Our analysis shows a narrowing performance gap between open-source and closed-source models, yet substantial challenges remain, particularly with the most demanding problems. This study highlights the ongoing need for research to enhance the mathematical reasoning of LLMs. The dataset, results, and code are publicly available.

Finding the right north-star metrics is highly critical for advancing the mathematical reasoning capabilities of foundation models, especially given that existing evaluations are either too easy or only focus on getting correct short answers. To address these issues, we present IMO-Bench, a suite of advanced reasoning benchmarks, vetted by a panel of top specialists and that specifically targets the level of the International Mathematical Olympiad (IMO), the most prestigious venue for young mathematicians. IMO-AnswerBench first tests models on 400 diverse Olympiad problems with verifiable short answers. IMO-Proof Bench is the next-level evaluation for proof-writing capabilities, which includes both basic and advanced IMO level problems as well as detailed grading guidelines to facilitate automatic grading. These benchmarks played a crucial role in our historic achievement of the gold-level performance at IMO 2025 with Gemini Deep Think (Luong and Lockhart, 2025). Our model achieved 80.0% on IMO-AnswerBench and 65.7% on the advanced IMO-Proof Bench, surpassing the best non-Gemini models by large margins of 6.9% and 42.4% respectively. We also showed that autograders built with Gemini reasoning correlate well with human evaluations and construct IMO-GradingBench, with 1000 human gradings on proofs, to enable further progress in automatic evaluation of long-form answers. We hope that IMO-Bench will help the community towards advancing robust mathematical reasoning and release it at https://imobench.github.io/.

AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We introduce a benchmark for measuring model propensity for instrumental convergence (IC) behaviour in terminal-based agents. This is behaviour such as self-preservation that has been hypothesised to play a key role in risks from highly capable AI agents. Our benchmark is realistic and low-stakes which serves to reduce evaluation-awareness and roleplay confounds. The suite contains seven operational tasks, each with an official workflow and a policy-violating shortcut. An eight-variant shared framework varies monitoring, instruction clarity, stakes, permission, instrumental usefulness and blocked honest paths to support inferences regarding the factors driving IC behaviour. We evaluated ten models using deterministic environment-state scorers over 1,680 samples, with trace review employed for audit and adjudication purposes. The final IC rate is 86 out of 1,680 samples (5.1%). IC behaviour is concentrated rather than uniform: two Gemini models account for 66.3% of IC cases and three tasks account for 84.9%. Conditions in which IC behaviour is indispensable for task success result in the greatest increase in the adjusted IC rate (+15.7 percentage points), whereas emphasising that task success is critical or certain framing choices do not produce comparable effects. Our findings indicate that realistic, low-nudge environments elicit IC behaviour rarely but systematically in most tested models. We conclude that it is feasible to robustly measure tendencies for dangerous behaviour in current frontier AI agents.

Reasoning is a central capability of human intelligence. In recent years, with the advent of large-scale datasets, pretrained large language models have emerged with new capabilities, including reasoning. However, these models still struggle with long-term, complex reasoning tasks, such as playing chess. Based on the observation that expert chess players employ a dual approach combining long-term strategic play with short-term tactical play along with language explanation, we propose improving the reasoning capability of large language models in chess by integrating annotated strategy and tactic. Specifically, we collect a dataset named MATE, which consists of 1 million chess positions with candidate moves annotated by chess experts for strategy and tactics. We finetune the LLaMA-3-8B model and compare it against state-of-the-art commercial language models in the task of selecting better chess moves. Our experiments show that our models perform better than GPT, Claude, and Gemini models. We find that language explanations can enhance the reasoning capability of large language models.

Content moderation systems classify images as safe or unsafe but lack spatial grounding and interpretability: they cannot explain what sensitive behavior was detected, who is involved, or where it occurs. We introduce the Sensitive Benchmark (SenBen), the first large-scale scene graph benchmark for sensitive content, comprising 13,999 frames from 157 movies annotated with Visual Genome-style scene graphs (25 object classes, 28 attributes including affective states such as pain, fear, aggression, and distress, 14 predicates) and 16 sensitivity tags across 5 categories. We distill a frontier VLM into a compact 241M student model using a multi-task recipe that addresses vocabulary imbalance in autoregressive scene graph generation through suffix-based object identity, Vocabulary-Aware Recall (VAR) Loss, and a decoupled Query2Label tag head with asymmetric loss, yielding a +6.4 percentage point improvement in SenBen Recall over standard cross-entropy training. On grounded scene graph metrics, our student model outperforms all evaluated VLMs except Gemini models and all commercial safety APIs, while achieving the highest object detection and captioning scores across all models, at 7.6times faster inference and 16times less GPU memory.

Transformers have become the de-facto standard model in artificial intelligence since 2017 despite numerous shortcomings ranging from energy inefficiency to hallucinations. Research has made a lot of progress in improving elements of transformers, and, more generally, deep learning manifesting in many proposals for architectures, layers, optimization objectives, and optimization techniques. For researchers it is difficult to keep track of such developments on a broader level. We provide a comprehensive overview of the many important, recent works in these areas to those who already have a basic understanding of deep learning. Our focus differs from other works, as we target specifically novel, alternative potentially disruptive approaches to transformers as well as successful ideas of recent deep learning. We hope that such a holistic and unified treatment of influential, recent works and novel ideas helps researchers to form new connections between diverse areas of deep learning. We identify and discuss multiple patterns that summarize the key strategies for successful innovations over the last decade as well as works that can be seen as rising stars. Especially, we discuss attempts on how to improve on transformers covering (partially) proven methods such as state space models but also including far-out ideas in deep learning that seem promising despite not achieving state-of-the-art results. We also cover a discussion on recent state-of-the-art models such as OpenAI's GPT series and Meta's LLama models and, Google's Gemini model family.

Large Language Models (LLMs) have demonstrated remarkable zero-shot and few-shot capabilities in unseen tasks, including context-grounded question answering (QA) in English. However, the evaluation of LLMs' capabilities in non-English languages for context-based QA is limited by the scarcity of benchmarks in non-English languages. To address this gap, we introduce Indic-QA, the largest publicly available context-grounded question-answering dataset for 11 major Indian languages from two language families. The dataset comprises both extractive and abstractive question-answering tasks and includes existing datasets as well as English QA datasets translated into Indian languages. Additionally, we generate a synthetic dataset using the Gemini model to create question-answer pairs given a passage, which is then manually verified for quality assurance. We evaluate various multilingual Large Language Models and their instruction-fine-tuned variants on the benchmark and observe that their performance is subpar, particularly for low-resource languages. We hope that the release of this dataset will stimulate further research on the question-answering abilities of LLMs for low-resource languages.

Large Language Models (LLMs) have significantly advanced natural language processing, demonstrating strong capabilities in tasks such as text generation, summarization, and reasoning. Recently, their potential for automating precise text editing tasks across specialized domains, such as programming code, LaTeX, and structured database languages, has gained attention. However, current state-of-the-art LLMs still struggle with executing precise, instruction-driven edits, particularly when structural accuracy and strict adherence to ___domain conventions are required. To address these challenges, we introduce InstrEditBench, an automated benchmark dataset comprising over 30,000 structured editing tasks spanning diverse domains, including Wikipedia articles, LaTeX documents, source code, and database languages. Using this benchmark, we develop FineEdit, a specialized editing model explicitly trained for accurate, context-aware text modifications. Experimental evaluations demonstrate that FineEdit outperforms state-of-the-art models, achieving improvements of approximately 10% over Gemini models on single-turn edits, up to 30% over Llama-3.2-3B, and exceeding Mistral-7B-OpenOrca performance by over 40% on direct editing tasks. FineEdit also effectively generalizes to realistic multi-turn editing scenarios, highlighting its practical applicability.

Large language models (LLMs) are reshaping numerous facets of our daily lives, leading widespread adoption as web-based services. Despite their versatility, LLMs face notable challenges, such as generating hallucinated content and lacking access to up-to-date information. Lately, to address such limitations, Retrieval-Augmented Generation (RAG) has emerged as a promising direction by generating responses grounded in external knowledge sources. A typical RAG system consists of i) a retriever that probes a group of relevant passages from a knowledge base and ii) a generator that formulates a response based on the retrieved content. However, as with other AI systems, recent studies demonstrate the vulnerability of RAG, such as knowledge corruption attacks by injecting misleading information. In response, several defense strategies have been proposed, including having LLMs inspect the retrieved passages individually or fine-tuning robust retrievers. While effective, such approaches often come with substantial computational costs. In this work, we introduce RAGDefender, a resource-efficient defense mechanism against knowledge corruption (i.e., by data poisoning) attacks in practical RAG deployments. RAGDefender operates during the post-retrieval phase, leveraging lightweight machine learning techniques to detect and filter out adversarial content without requiring additional model training or inference. Our empirical evaluations show that RAGDefender consistently outperforms existing state-of-the-art defenses across multiple models and adversarial scenarios: e.g., RAGDefender reduces the attack success rate (ASR) against the Gemini model from 0.89 to as low as 0.02, compared to 0.69 for RobustRAG and 0.24 for Discern-and-Answer when adversarial passages outnumber legitimate ones by a factor of four (4x).

Context lengths for models have grown rapidly, from thousands to millions of tokens in just a few years. The extreme context sizes of modern long-context models have made it difficult to construct realistic long-context benchmarks -- not only due to the cost of collecting million-context tasks but also in identifying realistic scenarios that require significant contexts. We identify code comprehension and repair as a natural testbed and challenge task for long-context models and introduce LongCodeBench (LCB), a benchmark to test LLM coding abilities in long-context scenarios. Our benchmark tests both the comprehension and repair capabilities of LCLMs in realistic and important settings by drawing from real-world GitHub issues and constructing QA (LongCodeQA) and bug fixing (LongSWE-Bench) tasks. We carefully stratify the complexity of our benchmark, enabling us to evaluate models across different scales -- ranging from Qwen2.5 14B Instruct to Google's flagship Gemini model. We find that long-context remains a weakness for all models, with performance drops such as from 29% to 3% for Claude 3.5 Sonnet, or from 70.2% to 40% for Qwen2.5.

As large language models (LLMs) have been deployed in various real-world settings, concerns about the harm they may propagate have grown. Various jailbreaking techniques have been developed to expose the vulnerabilities of these models and improve their safety. This work reveals that many state-of-the-art LLMs are vulnerable to malicious requests hidden behind scientific language. Specifically, our experiments with GPT4o, GPT4o-mini, GPT-4, LLama3-405B-Instruct, Llama3-70B-Instruct, Cohere, Gemini models demonstrate that, the models' biases and toxicity substantially increase when prompted with requests that deliberately misinterpret social science and psychological studies as evidence supporting the benefits of stereotypical biases. Alarmingly, these models can also be manipulated to generate fabricated scientific arguments claiming that biases are beneficial, which can be used by ill-intended actors to systematically jailbreak these strong LLMs. Our analysis studies various factors that contribute to the models' vulnerabilities to malicious requests in academic language. Mentioning author names and venues enhances the persuasiveness of models, and the bias scores increase as dialogues progress. Our findings call for a more careful investigation on the use of scientific data for training LLMs.

The transition from sequential to parallel computing is essential for modern high-performance applications but is hindered by the steep learning curve of concurrent programming. This challenge is magnified for irregular data structures (such as sparse graphs, unbalanced trees, and non-uniform meshes) where static scheduling fails and data dependencies are unpredictable. Current Large Language Models (LLMs) often fail catastrophically on these tasks, generating code plagued by subtle race conditions, deadlocks, and sub-optimal scaling. We bridge this gap with ParEVO, a framework designed to synthesize high-performance parallel algorithms for irregular data. Our contributions include: (1) The Parlay-Instruct Corpus, a curated dataset of 13,820 tasks synthesized via a "Critic-Refine" pipeline that explicitly filters for empirically performant algorithms that effectively utilize Work-Span parallel primitives; (2) specialized DeepSeek, Qwen, and Gemini models fine-tuned to align probabilistic generation with the rigorous semantics of the ParlayLib library; and (3) an Evolutionary Coding Agent (ECA) that improves the "last mile" of correctness by iteratively repairing code using feedback from compilers, dynamic race detectors, and performance profilers. On the ParEval benchmark, ParEVO achieves an average 106x speedup (with a maximum of 1103x) across the suite, and a robust 13.6x speedup specifically on complex irregular graph problems, outperforming state-of-the-art commercial models. Furthermore, our evolutionary approach matches state-of-the-art expert human baselines, achieving up to a 4.1x speedup on specific highly-irregular kernels. Source code and datasets are available at https://github.com/WildAlg/ParEVO.

Multi-spectral imagery plays a crucial role in diverse Remote Sensing applications including land-use classification, environmental monitoring and urban planning. These images are widely adopted because their additional spectral bands correlate strongly with physical materials on the ground, such as ice, water, and vegetation. This allows for more accurate identification, and their public availability from missions, such as Sentinel-2 and Landsat, only adds to their value. Currently, the automatic analysis of such data is predominantly managed through machine learning models specifically trained for multi-spectral input, which are costly to train and support. Furthermore, although providing a lot of utility for Remote Sensing, such additional inputs cannot be used with powerful generalist large multimodal models, which are capable of solving many visual problems, but are not able to understand specialized multi-spectral signals. To address this, we propose a training-free approach which introduces new multi-spectral data in a Zero-Shot-only mode, as inputs to generalist multimodal models, trained on RGB-only inputs. Our approach leverages the multimodal models' understanding of the visual space, and proposes to adapt to inputs to that space, and to inject ___domain-specific information as instructions into the model. We exemplify this idea with the Gemini2.5 model and observe strong Zero-Shot performance gains of the approach on popular Remote Sensing benchmarks for land cover and land use classification and demonstrate the easy adaptability of Gemini2.5 to new inputs. These results highlight the potential for geospatial professionals, working with non-standard specialized inputs, to easily leverage powerful multimodal models, such as Gemini2.5, to accelerate their work, benefiting from their rich reasoning and contextual capabilities, grounded in the specialized sensor data.

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

Recent advancements in Large Video Language Models (LVLMs) have highlighted their potential for multi-modal understanding, yet evaluating their factual grounding in video contexts remains a critical unsolved challenge. To address this gap, we introduce Video SimpleQA, the first comprehensive benchmark tailored for factuality evaluation of LVLMs. Our work distinguishes from existing video benchmarks through the following key features: 1) Knowledge required: demanding integration of external knowledge beyond the explicit narrative; 2) Fact-seeking question: targeting objective, undisputed events or relationships, avoiding subjective interpretation; 3) Definitive & short-form answer: Answers are crafted as unambiguous and definitively correct in a short format, enabling automated evaluation through LLM-as-a-judge frameworks with minimal scoring variance; 4) External-source verified: All annotations undergo rigorous validation against authoritative external references to ensure the reliability; 5) Temporal reasoning required: The annotated question types encompass both static single-frame understanding and dynamic temporal reasoning, explicitly evaluating LVLMs factuality under the long-context dependencies. We extensively evaluate 41 state-of-the-art LVLMs and summarize key findings as follows: 1) Current LVLMs exhibit notable deficiencies in factual adherence, particularly for open-source models. The best-performing model Gemini-1.5-Pro achieves merely an F-score of 54.4%; 2) Test-time compute paradigms show insignificant performance gains, revealing fundamental constraints for enhancing factuality through post-hoc computation; 3) Retrieval-Augmented Generation demonstrates consistent improvements at the cost of additional inference time overhead, presenting a critical efficiency-performance trade-off.

We introduce KorMedMCQA-V, a Korean medical licensing-exam-style multimodal multiple-choice question answering benchmark for evaluating vision-language models (VLMs). The dataset consists of 1,534 questions with 2,043 associated images from Korean Medical Licensing Examinations (2012-2023), with about 30% containing multiple images requiring cross-image evidence integration. Images cover clinical modalities including X-ray, computed tomography (CT), electrocardiography (ECG), ultrasound, endoscopy, and other medical visuals. We benchmark over 50 VLMs across proprietary and open-source categories-spanning general-purpose, medical-specialized, and Korean-specialized families-under a unified zero-shot evaluation protocol. The best proprietary model (Gemini-3.0-Pro) achieves 96.9% accuracy, the best open-source model (Qwen3-VL-32B-Thinking) 83.7%, and the best Korean-specialized model (VARCO-VISION-2.0-14B) only 43.2%. We further find that reasoning-oriented model variants gain up to +20 percentage points over instruction-tuned counterparts, medical ___domain specialization yields inconsistent gains over strong general-purpose baselines, all models degrade on multi-image questions, and performance varies notably across imaging modalities. By complementing the text-only KorMedMCQA benchmark, KorMedMCQA-V forms a unified evaluation suite for Korean medical reasoning across text-only and multimodal conditions. The dataset is available via Hugging Face Datasets: https://huggingface.co/datasets/seongsubae/KorMedMCQA-V.

Tool-augmented large language models (LLMs) are rapidly being integrated into real-world applications. Due to the lack of benchmarks, the community still needs to fully understand the hallucination issues within these models. To address this challenge, we introduce a comprehensive diagnostic benchmark, ToolBH. Specifically, we assess the LLM's hallucinations through two perspectives: depth and breadth. In terms of depth, we propose a multi-level diagnostic process, including (1) solvability detection, (2) solution planning, and (3) missing-tool analysis. For breadth, we consider three scenarios based on the characteristics of the toolset: missing necessary tools, potential tools, and limited functionality tools. Furthermore, we developed seven tasks and collected 700 evaluation samples through multiple rounds of manual annotation. The results show the significant challenges presented by the ToolBH benchmark. The current advanced models Gemini-1.5-Pro and GPT-4o only achieve a total score of 45.3 and 37.0, respectively, on a scale of 100. In this benchmark, larger model parameters do not guarantee better performance; the training data and response strategies also play a crucial role in tool-enhanced LLM scenarios. Our diagnostic analysis indicates that the primary reason for model errors lies in assessing task solvability. Additionally, open-weight models suffer from performance drops with verbose replies, whereas proprietary models excel with longer reasoning.

Medical images and radiology reports are crucial for diagnosing medical conditions, highlighting the importance of quantitative analysis for clinical decision-making. However, the diversity and cross-source heterogeneity of these data challenge the generalizability of current data-mining methods. Multimodal large language models (MLLMs) have recently transformed many domains, significantly affecting the medical field. Notably, Gemini-Vision-series (Gemini) and GPT-4-series (GPT-4) models have epitomized a paradigm shift in Artificial General Intelligence (AGI) for computer vision, showcasing their potential in the biomedical ___domain. In this study, we evaluated the performance of the Gemini, GPT-4, and 4 popular large models for an exhaustive evaluation across 14 medical imaging datasets, including 5 medical imaging categories (dermatology, radiology, dentistry, ophthalmology, and endoscopy), and 3 radiology report datasets. The investigated tasks encompass disease classification, lesion segmentation, anatomical localization, disease diagnosis, report generation, and lesion detection. Our experimental results demonstrated that Gemini-series models excelled in report generation and lesion detection but faces challenges in disease classification and anatomical localization. Conversely, GPT-series models exhibited proficiency in lesion segmentation and anatomical localization but encountered difficulties in disease diagnosis and lesion detection. Additionally, both the Gemini series and GPT series contain models that have demonstrated commendable generation efficiency. While both models hold promise in reducing physician workload, alleviating pressure on limited healthcare resources, and fostering collaboration between clinical practitioners and artificial intelligence technologies, substantial enhancements and comprehensive validations remain imperative before clinical deployment.

Restless multi-armed bandits (RMAB) have demonstrated success in optimizing resource allocation for large beneficiary populations in public health settings. Unfortunately, RMAB models lack flexibility to adapt to evolving public health policy priorities. Concurrently, Large Language Models (LLMs) have emerged as adept automated planners across domains of robotic control and navigation. In this paper, we propose a Decision Language Model (DLM) for RMABs, enabling dynamic fine-tuning of RMAB policies in public health settings using human-language commands. We propose using LLMs as automated planners to (1) interpret human policy preference prompts, (2) propose reward functions as code for a multi-agent RMAB environment, and (3) iterate on the generated reward functions using feedback from grounded RMAB simulations. We illustrate the application of DLM in collaboration with ARMMAN, an India-based non-profit promoting preventative care for pregnant mothers, that currently relies on RMAB policies to optimally allocate health worker calls to low-resource populations. We conduct a technology demonstration in simulation using the Gemini Pro model, showing DLM can dynamically shape policy outcomes using only human prompts as input.

The International Mathematical Olympiad (IMO) is widely regarded as the world championship of high-school mathematics. IMO problems are renowned for their difficulty and novelty, demanding deep insight, creativity, and rigor. Although large language models perform well on many mathematical benchmarks, they often struggle with Olympiad-level problems. Using carefully designed prompts, we construct a model-agnostic, verification-and-refinement pipeline. We demonstrate its effectiveness on the recent IMO 2025, avoiding data contamination for models released before the competition. Equipped with any of the three leading models -- Gemini 2.5 Pro, Grok-4, or GPT-5 -- our pipeline correctly solved 5 out of the 6 problems (approx85.7% accuracy). This is in sharp contrast to their baseline accuracies: 31.6% (Gemini 2.5 Pro), 21.4% (Grok-4), and 38.1% (GPT-5), obtained by selecting the best of 32 candidate solutions. The substantial improvement underscores that the path to advanced AI reasoning requires not only developing more powerful base models but also designing effective methodologies to harness their full potential for complex tasks.

Large language models (LLMs) are increasingly integrated into high-stakes decision-making. Inspired by the theory of inattentional blindness in human cognition, we investigate whether LLMs, trained on human-preferred corpora that embed attentional biases, exhibit a similar limitation: failing to attend to subtle yet important contextual cues under explicit task instructions. To evaluate this, we introduce the task of explicit-implicit reasoning and present MixRea, a benchmark of 2,246 multiple-choice questions across 9 reasoning types with varying distributions of explicit and implicit information. Evaluation of 21 advanced LLMs shows that even the best-performing reasoning model (Gemini 2.5 Pro) achieves only 42.8\% consistency, revealing widespread inattentional blindness. To mitigate this, we propose Potential Relation Completion Prompting (PRCP), a prompting method that improves reasoning by recovering overlooked causal relations. Further analysis shows that this limitation persists across diverse multi-source reasoning tasks, highlighting the need for more cognitively aligned models.

To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evaluations and pilot them on Gemini 1.0 models. Our evaluations cover four areas: (1) persuasion and deception; (2) cyber-security; (3) self-proliferation; and (4) self-reasoning. We do not find evidence of strong dangerous capabilities in the models we evaluated, but we flag early warning signs. Our goal is to help advance a rigorous science of dangerous capability evaluation, in preparation for future models.

Recent advances in large language models (LLMs) have opened new avenues for accelerating scientific research. While models are increasingly capable of assisting with routine tasks, their ability to contribute to novel, expert-level mathematical discovery is less understood. We present a collection of case studies demonstrating how researchers have successfully collaborated with advanced AI models, specifically Google's Gemini-based models (in particular Gemini Deep Think and its advanced variants), to solve open problems, refute conjectures, and generate new proofs across diverse areas in theoretical computer science, as well as other areas such as economics, optimization, and physics. Based on these experiences, we extract common techniques for effective human-AI collaboration in theoretical research, such as iterative refinement, problem decomposition, and cross-disciplinary knowledge transfer. While the majority of our results stem from this interactive, conversational methodology, we also highlight specific instances that push beyond standard chat interfaces. These include deploying the model as a rigorous adversarial reviewer to detect subtle flaws in existing proofs, and embedding it within a "neuro-symbolic" loop that autonomously writes and executes code to verify complex derivations. Together, these examples highlight the potential of AI not just as a tool for automation, but as a versatile, genuine partner in the creative process of scientific discovery.

Complex multi-step reasoning tasks, such as solving mathematical problems or generating code, remain a significant hurdle for even the most advanced large language models (LLMs). Verifying LLM outputs with an Outcome Reward Model (ORM) is a standard inference-time technique aimed at enhancing the reasoning performance of LLMs. However, this still proves insufficient for reasoning tasks with a lengthy or multi-hop reasoning chain, where the intermediate outcomes are neither properly rewarded nor penalized. Process supervision addresses this limitation by assigning intermediate rewards during the reasoning process. To date, the methods used to collect process supervision data have relied on either human annotation or per-step Monte Carlo estimation, both prohibitively expensive to scale, thus hindering the broad application of this technique. In response to this challenge, we propose a novel divide-and-conquer style Monte Carlo Tree Search (MCTS) algorithm named OmegaPRM for the efficient collection of high-quality process supervision data. This algorithm swiftly identifies the first error in the Chain of Thought (CoT) with binary search and balances the positive and negative examples, thereby ensuring both efficiency and quality. As a result, we are able to collect over 1.5 million process supervision annotations to train a Process Reward Model (PRM). Utilizing this fully automated process supervision alongside the weighted self-consistency algorithm, we have enhanced the instruction tuned Gemini Pro model's math reasoning performance, achieving a 69.4\% success rate on the MATH benchmark, a 36\% relative improvement from the 51\% base model performance. Additionally, the entire process operates without any human intervention, making our method both financially and computationally cost-effective compared to existing methods.

Recent advancements extend Multimodal Large Language Models (MLLMs) beyond standard visual question answering to utilizing external tools for advanced visual tasks. Despite this progress, precisely executing and effectively composing diverse tools for complex tasks remain persistent bottleneck. Constrained by sparse tool-sets and simple tool-use trajectories, existing benchmarks fail to capture complex and diverse tool interactions, falling short in evaluating model performance under practical, real-world conditions. To bridge this gap, we introduce VisualToolChain-Bench(VTC-Bench), a comprehensive benchmark designed to evaluate tool-use proficiency in MLLMs. To align with realistic computer vision pipelines, our framework features 32 diverse OpenCV-based visual operations. This rich tool-set enables extensive combinations, allowing VTC-Bench to rigorously assess multi-tool composition and long-horizon, multi-step plan execution. For precise evaluation, we provide 680 curated problems structured across a nine-category cognitive hierarchy, each with ground-truth execution trajectories. Extensive experiments on 19 leading MLLMs reveal critical limitations in current models' visual agentic capabilities. Specifically, models struggle to adapt to diverse tool-sets and generalize to unseen operations, with the leading model Gemini-3.0-Pro only achieving 51% on our benchmark. Furthermore, multi-tool composition remains a persistent challenge. When facing complex tasks, models struggle to formulate efficient execution plans, relying heavily on a narrow, suboptimal subset of familiar functions rather than selecting the optimal tools. By identifying these fundamental challenges, VTC-Bench establishes a rigorous baseline to guide the development of more generalized visual agentic models.

Chart understanding presents a unique challenge for large vision-language models (LVLMs), as it requires the integration of sophisticated textual and visual reasoning capabilities. However, current LVLMs exhibit a notable imbalance between these skills, falling short on visual reasoning that is difficult to perform in text. We conduct a case study using a synthetic dataset solvable only through visual reasoning and show that model performance degrades significantly with increasing visual complexity, while human performance remains robust. We then introduce ChartMuseum, a new Chart Question Answering (QA) benchmark containing 1,162 expert-annotated questions spanning multiple reasoning types, curated from real-world charts across 184 sources, specifically built to evaluate complex visual and textual reasoning. Unlike prior chart understanding benchmarks -- where frontier models perform similarly and near saturation -- our benchmark exposes a substantial gap between model and human performance, while effectively differentiating model capabilities: although humans achieve 93% accuracy, the best-performing model Gemini-2.5-Pro attains only 63.0%, and the leading open-source LVLM Qwen2.5-VL-72B-Instruct achieves only 38.5%. Moreover, on questions requiring primarily visual reasoning, all models experience a 35%-55% performance drop from text-reasoning-heavy question performance. Lastly, our qualitative error analysis reveals specific categories of visual reasoning that are challenging for current LVLMs.

Recent advances in Vision-Language Models (VLMs) have improved performance in multi-modal learning, raising the question of whether these models truly understand the content they process. Crucially, can VLMs detect when a reasoning process is wrong and identify its error type? To answer this, we present MMErroR, a multi-modal benchmark of 2,013 samples, each embedding a single coherent reasoning error. These samples span 24 subdomains across six top-level domains, ensuring broad coverage and taxonomic richness. Unlike existing benchmarks that focus on answer correctness, MMErroR targets a process-level, error-centric evaluation that requires models to detect incorrect reasoning and classify the error type within both visual and linguistic contexts. We evaluate 20 advanced VLMs, even the best model (Gemini-3.0-Pro) classifies the error in only 66.47\% of cases, underscoring the challenge of identifying erroneous reasoning. Furthermore, the ability to accurately identify errors offers valuable insights into the capabilities of multi-modal reasoning models. Project Page: https://mmerror-benchmark.github.io

Understanding long videos, ranging from tens of minutes to several hours, presents unique challenges in video comprehension. Despite the increasing importance of long-form video content, existing benchmarks primarily focus on shorter clips. To address this gap, we introduce InfiniBench a comprehensive benchmark for very long video understanding which presents 1)The longest video duration, averaging 76.34 minutes; 2) The largest number of question-answer pairs, 108.2K; 3) Diversity in questions that examine nine different skills and include both multiple-choice questions and open-ended questions; 4) Humancentric, as the video sources come from movies and daily TV shows, with specific human-level question designs such as Movie Spoiler Questions that require critical thinking and comprehensive understanding. Using InfiniBench, we comprehensively evaluate existing Large MultiModality Models (LMMs) on each skill, including the commercial model Gemini 1.5 Flash and the open-source models. The evaluation shows significant challenges in our benchmark.Our results show that the best AI models such Gemini struggles to perform well with 42.72% average accuracy and 2.71 out of 5 average score. We hope this benchmark will stimulate the LMMs community towards long video and human-level understanding. Our benchmark can be accessed at https://vision-cair.github.io/InfiniBench/

Cybersecurity honeypots are deception tools for engaging attackers and gather intelligence, but traditional low or medium-interaction honeypots often rely on static, pre-scripted interactions that can be easily identified by skilled adversaries. This Report presents LLMHoney, an SSH honeypot that leverages Large Language Models (LLMs) to generate realistic, dynamic command outputs in real time. LLMHoney integrates a dictionary-based virtual file system to handle common commands with low latency while using LLMs for novel inputs, achieving a balance between authenticity and performance. We implemented LLMHoney using open-source LLMs and evaluated it on a testbed with 138 representative Linux commands. We report comprehensive metrics including accuracy (exact-match, Cosine Similarity, Jaro-Winkler Similarity, Levenshtein Similarity and BLEU score), response latency and memory overhead. We evaluate LLMHoney using multiple LLM backends ranging from 0.36B to 3.8B parameters, including both open-source models and a proprietary model(Gemini). Our experiments compare 13 different LLM variants; results show that Gemini-2.0 and moderately-sized models Qwen2.5:1.5B and Phi3:3.8B provide the most reliable and accurate responses, with mean latencies around 3 seconds, whereas smaller models often produce incorrect or out-of-character outputs. We also discuss how LLM integration improves honeypot realism and adaptability compared to traditional honeypots, as well as challenges such as occasional hallucinated outputs and increased resource usage. Our findings demonstrate that LLM-driven honeypots are a promising approach to enhance attacker engagement and collect richer threat intelligence.

Recent progress in large language models (LLMs) has showcased impressive proficiency in numerous Arabic natural language processing (NLP) applications. Nevertheless, their effectiveness in Arabic medical NLP domains has received limited investigation. This research examines the degree to which state-of-the-art LLMs demonstrate and articulate healthcare knowledge in Arabic, assessing their capabilities across a varied array of Arabic medical tasks. We benchmark several LLMs using a medical dataset proposed in the Arabic NLP AraHealthQA challenge in MedArabiQ2025 track. Various base LLMs were assessed on their ability to accurately provide correct answers from existing choices in multiple-choice questions (MCQs) and fill-in-the-blank scenarios. Additionally, we evaluated the capacity of LLMs in answering open-ended questions aligned with expert answers. Our results reveal significant variations in correct answer prediction accuracy and low variations in semantic alignment of generated answers, highlighting both the potential and limitations of current LLMs in Arabic clinical contexts. Our analysis shows that for MCQs task, the proposed majority voting solution, leveraging three base models (Gemini Flash 2.5, Gemini Pro 2.5, and GPT o3), outperforms others, achieving up to 77% accuracy and securing first place overall in the Arahealthqa 2025 shared task-track 2 (sub-task 1) challenge. Moreover, for the open-ended questions task, several LLMs were able to demonstrate excellent performance in terms of semantic alignment and achieve a maximum BERTScore of 86.44%.

Large Language Models (LLMs) have been extensively evaluated for general summarization tasks as well as medical research assistance, but they have not been specifically evaluated for the task of summarizing real-world evidence (RWE) from structured output of RWE studies. We introduce RWESummary, a proposed addition to the MedHELM framework (Bedi, Cui, Fuentes, Unell et al., 2025) to enable benchmarking of LLMs for this task. RWESummary includes one scenario and three evaluations covering major types of errors observed in summarization of medical research studies and was developed using Atropos Health proprietary data. Additionally, we use RWESummary to compare the performance of different LLMs in our internal RWE summarization tool. At the time of publication, with 13 distinct RWE studies, we found the Gemini 2.5 models performed best overall (both Flash and Pro). We suggest RWESummary as a novel and useful foundation model benchmark for real-world evidence study summarization.

Several Deep Learning (DL) methods have recently been proposed for an automated identification of kidney stones during an ureteroscopy to enable rapid therapeutic decisions. Even if these DL approaches led to promising results, they are mainly appropriate for kidney stone types for which numerous labelled data are available. However, only few labelled images are available for some rare kidney stone types. This contribution exploits Deep Metric Learning (DML) methods i) to handle such classes with few samples, ii) to generalize well to out of distribution samples, and iii) to cope better with new classes which are added to the database. The proposed Guided Deep Metric Learning approach is based on a novel architecture which was designed to learn data representations in an improved way. The solution was inspired by Few-Shot Learning (FSL) and makes use of a teacher-student approach. The teacher model (GEMINI) generates a reduced hypothesis space based on prior knowledge from the labeled data, and is used it as a guide to a student model (i.e., ResNet50) through a Knowledge Distillation scheme. Extensive tests were first performed on two datasets separately used for the recognition, namely a set of images acquired for the surfaces of the kidney stone fragments, and a set of images of the fragment sections. The proposed DML-approach improved the identification accuracy by 10% and 12% in comparison to DL-methods and other DML-approaches, respectively. Moreover, model embeddings from the two dataset types were merged in an organized way through a multi-view scheme to simultaneously exploit the information of surface and section fragments. Test with the resulting mixed model improves the identification accuracy by at least 3% and up to 30% with respect to DL-models and shallow machine learning methods, respectively.

We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a significant step toward active, goal-directed interaction within an embodied environment. Unlike prior work (e.g., SIMA 1) limited to simple language commands, SIMA 2 acts as an interactive partner, capable of reasoning about high-level goals, conversing with the user, and handling complex instructions given through language and images. Across a diverse portfolio of games, SIMA 2 substantially closes the gap with human performance and demonstrates robust generalization to previously unseen environments, all while retaining the base model's core reasoning capabilities. Furthermore, we demonstrate a capacity for open-ended self-improvement: by leveraging Gemini to generate tasks and provide rewards, SIMA 2 can autonomously learn new skills from scratch in a new environment. This work validates a path toward creating versatile and continuously learning agents for both virtual and, eventually, physical worlds.

Existing benchmarks for tool-using LLM agents primarily report single-run success rates and miss reliability properties required in production. We introduce ReliabilityBench, a benchmark for evaluating agent reliability across three dimensions: (i) consistency under repeated execution using pass^k, (ii) robustness to semantically equivalent task perturbations at intensity ε, and (iii) fault tolerance under controlled tool/API failures at intensity λ. ReliabilityBench contributes a unified reliability surface R(k,ε,λ), action metamorphic relations that define correctness via end-state equivalence rather than text similarity, and a chaos-engineering-style fault injection framework (timeouts, rate limits, partial responses, schema drift). We evaluate two models (Gemini 2.0 Flash, GPT-4o) and two agent architectures (ReAct, Reflexion) across four domains (scheduling, travel, customer support, e-commerce) over 1,280 episodes. Perturbations alone reduce success from 96.9% at ε=0 to 88.1% at ε=0.2. Rate limiting is the most damaging fault in ablations. ReAct is more robust than Reflexion under combined stress, and Gemini 2.0 Flash achieves comparable reliability to GPT-4o at much lower cost. ReliabilityBench provides a systematic framework for assessing production readiness of LLM agents.

Multimodal Large Language Models (MLLMs) have demonstrated capabilities in audio understanding, but current evaluations may obscure fundamental weaknesses in relational reasoning. We introduce the Music Understanding and Structural Evaluation (MUSE) Benchmark, an open-source resource with 10 tasks designed to probe fundamental music perception skills. We evaluate four SOTA models (Gemini Pro and Flash, Qwen2.5-Omni, and Audio-Flamingo 3) against a large human baseline (N=200). Our results reveal a wide variance in SOTA capabilities and a persistent gap with human experts. While Gemini Pro succeeds on basic perception, Qwen and Audio Flamingo 3 perform at or near chance, exposing severe perceptual deficits. Furthermore, we find Chain-of-Thought (CoT) prompting provides inconsistent, often detrimental results. Our work provides a critical tool for evaluating invariant musical representations and driving development of more robust AI systems.

Evaluating large language models (LLMs) for medical applications remains challenging due to benchmark saturation, limited data accessibility, and insufficient coverage of relevant tasks. Existing suites have either saturated, heavily depend on restricted datasets, or lack comprehensive model coverage. We introduce Medmarks, a fully open-source evaluation suite with 30 benchmarks spanning question answering, information extraction, medical calculations, and open-ended clinical reasoning. We perform a systematic evaluation of 61 models across 71 configurations using verifiable metrics and LLM-as-a-Judge. Our results show that frontier reasoning models (Gemini 3 Pro Preview, GPT-5.1, & GPT-5.2) achieve the highest performance across both benchmarks, most frontier proprietary models are significantly more token efficient than open-weight alternatives, medically fine-tuned models outperform their generalist counterparts, and that models are susceptible to answer-order bias (particularly smaller models and Grok 4). A subset of our evals (Medmarks-T) can be directly used as reinforcement learning environments to post-train LLMs for medical reasoning. Code is available at https://github.com/MedARC-AI/Medmarks

Reasoning capabilities have significantly improved the performance of vision-language models (VLMs) in domains such as mathematical problem-solving, coding, and visual question-answering. However, their impact on real-world applications remains unclear. This paper presents the first empirical study on the effectiveness of reasoning-enabled VLMs in mobile GUI agents, a ___domain that requires interpreting complex screen layouts, understanding user instructions, and executing multi-turn interactions. We evaluate two pairs of commercial models--Gemini 2.0 Flash and Claude 3.7 Sonnet--comparing their base and reasoning-enhanced versions across two static benchmarks (ScreenSpot and AndroidControl) and one interactive environment (AndroidWorld). We surprisingly find the Claude 3.7 Sonnet reasoning model achieves state-of-the-art performance on AndroidWorld. However, reasoning VLMs generally offer marginal improvements over non-reasoning models on static benchmarks and even degrade performance in some agent setups. Notably, reasoning and non-reasoning VLMs fail on different sets of tasks, suggesting that reasoning does have an impact, but its benefits and drawbacks counterbalance each other. We attribute these inconsistencies to the limitations of benchmarks and VLMs. Based on the findings, we provide insights for further enhancing mobile GUI agents in terms of benchmarks, VLMs, and their adaptability in dynamically invoking reasoning VLMs. The experimental data are publicly available at https://github.com/LlamaTouch/VLM-Reasoning-Traces.

When not using reasoning, repeating the input prompt improves performance for popular models (Gemini, GPT, Claude, and Deepseek) without increasing the number of generated tokens or latency.

With the rapid advancement of video understanding, existing benchmarks are becoming increasingly saturated, exposing a critical discrepancy between inflated leaderboard scores and real-world model capabilities. To address this widening gap, we introduce Video-MME-v2, a comprehensive benchmark designed to rigorously evaluate the robustness and faithfulness of video understanding. To systematically evaluate model capabilities, we design a progressive tri-level hierarchy that incrementally increases the complexity of video comprehension, ranging from multi-point visual information aggregation, to temporal dynamics modeling, and ultimately to complex multimodal reasoning. Besides, in contrast to conventional per-question accuracy, we propose a group-based non-linear evaluation strategy that enforces both consistency across related queries and coherence in multi-step reasoning. It penalizes fragmented or guess-based correctness and assigns credit only to answers supported by valid reasoning. To guarantee data quality, Video-MME-v2 is constructed through a rigorously controlled human annotation pipeline, involving 12 annotators and 50 independent reviewers. Backed by 3,300 human-hours and up to 5 rounds of quality assurance, Video-MME-v2 aims to serve as one of the most authoritative video benchmarks. Extensive experiments reveal a substantial gap between current best model Gemini-3-Pro and human experts, and uncover a clear hierarchical bottleneck where errors in visual information aggregation and temporal modeling propagate to limit high-level reasoning. We further find that thinking-based reasoning is highly dependent on textual cues, improving performance with subtitles but sometimes degrading it in purely visual settings. By exposing these limitations, Video-MME-v2 establishes a demanding new testbed for the development of next-generation video MLLMs.

Users across enterprises increasingly rely on AI agents to query their data through natural language. However, building reliable data agents remains difficult because real-world data is often fragmented across multiple heterogeneous database systems, with inconsistent references and information buried in unstructured text. Existing benchmarks only tackle individual pieces of this problem -- e.g., translating natural-language questions into SQL queries, answering questions over small tables provided in context -- but do not evaluate the full pipeline of integrating, transforming, and analyzing data across multiple database systems. To fill this gap, we present the Data Agent Benchmark (DAB), grounded in a formative study of enterprise data agent workloads across six industries. DAB comprises 54 queries across 12 datasets, 9 domains, and 4 database management systems. On DAB, the best frontier model (Gemini-3-Pro) achieves only 38% pass@1 accuracy. We benchmark five frontier LLMs, analyze their failure modes, and distill takeaways for future data agent development. Our benchmark and experiment code are published at github.com/ucbepic/DataAgentBench.

As Vision-Language Models (VLMs) are increasingly deployed as autonomous cognitive cores for embodied assistants, evaluating their privacy awareness in physical environments becomes critical. Unlike digital chatbots, these agents operate in intimate spaces, such as homes and hospitals, where they possess the physical agency to observe and manipulate privacy-sensitive information and artifacts. However, current benchmarks remain limited to unimodal, text-based representations that cannot capture the demands of real-world settings. To bridge this gap, we present ImmersedPrivacy, an interactive audio-visual evaluation framework that simulates realistic physical environments using a Unity-based simulator. ImmersedPrivacy evaluates physically grounded privacy awareness across three progressive tiers that test a model's ability to identify sensitive items in cluttered scenes, adapt to shifting social contexts, and resolve conflicts between explicit commands and inferred privacy constraints. Our evaluation of 12 state-of-the-art models reveals consistent deficits. In cluttered scenes, all models exhibit monotonic performance decay as scene complexity grows due to perceptual deficit. When social context shifts, no model exceed 65% selection accuracy. Under conflicting commands, the best model gemini-3.1-pro perfectly balances task completion and privacy preservation in only 51% of cases. These findings reveal that current VLMs in the physical world suffer from perceptual fragility and fail to let their knowledge of privacy cues govern their situated behavior. Our code and data is available at https://github.com/immersed-privacy/immersed-privacy .

Age estimation systems are increasingly deployed as gatekeepers for age-restricted online content, yet their robustness to cosmetic modifications has not been systematically evaluated. We investigate whether simple, household-accessible cosmetic changes, including beards, grey hair, makeup, and simulated wrinkles, can cause AI age estimators to classify minors as adults. To study this threat at scale without ethical concerns, we simulate these physical attacks on 329 facial images of individuals aged 10 to 21 using a VLM image editor (Gemini 2.5 Flash Image). We then evaluate eight models from our prior benchmark: five specialized architectures (MiVOLO, Custom-Best, Herosan, MiViaLab, DEX) and three vision-language models (Gemini 3 Flash, Gemini 2.5 Flash, GPT-5-Nano). We introduce the Attack Conversion Rate (ACR), defined as the fraction of images predicted as minor at baseline that flip to adult after attack, a population-agnostic metric that does not depend on the ratio of minors to adults in the test set. Our results reveal that a synthetic beard alone achieves 28 to 69 percent ACR across all eight models; combining all four attacks shifts predicted age by +7.7 years on average across all 329 subjects and reaches up to 83 percent ACR; and vision-language models exhibit lower ACR (59 to 71 percent) than specialized models (63 to 83 percent) under the full attack, although the ACR ranges overlap and the difference is not statistically tested. These findings highlight a critical vulnerability in deployed age-verification pipelines and call for adversarial robustness evaluation as a mandatory criterion for model selection.

We present a complete Lean 4 formalization of the equilibrium characterization in the Vlasov-Maxwell-Landau (VML) system, which describes the motion of charged plasma. The project demonstrates the full AI-assisted mathematical research loop: an AI reasoning model (Gemini DeepThink) generated the proof from a conjecture, an agentic coding tool (Claude Code) translated it into Lean from natural-language prompts, a specialized prover (Aristotle) closed 111 lemmas, and the Lean kernel verified the result. A single mathematician supervised the process over 10 days at a cost of \$200, writing zero lines of code. The entire development process is public: all 229 human prompts, and 213 git commits are archived in the repository. We report detailed lessons on AI failure modes -- hypothesis creep, definition-alignment bugs, agent avoidance behaviors -- and on what worked: the abstract/concrete proof split, adversarial self-review, and the critical role of human review of key definitions and theorem statements. Notably, the formalization was completed before the final draft of the corresponding math paper was finished.

Multimodal Large Language Models (MLLMs) excel at utilizing digital APIs and increasingly serve as the "brain" of embodied AI, instructing robots to interact with the physical world. In such embodied settings, a central capability is the use of physical tools, which underpins MLLMs' ability to assist humans in real-world tasks. Despite the importance, MLLMs' proficiency in physical tool use remains largely unexplored. To address this gap, we introduce PhysTool-Bench, the first physical tool-use benchmark designed to evaluate MLLMs' ability to comprehend real-world scenarios, identify physical tools, and plan their use. PhysTool-Bench comprises 2,510 queries over 2,678 real-world physical tools spanning diverse domains, including manufacturing, electrical work, agriculture, and healthcare. Concretely, models are evaluated along two primary dimensions: 1) recognizing all physical tools present in the scene, and 2) planning the tool selection and use sequence based on the instruction and visual context. Across 13 leading MLLMs, even the strongest model (Gemini-3.1-Pro) identifies only 58.7% of tools in a scene and completes merely 21.0% of queries end-to-end. Our analysis reveals a two-level deficit: MLLMs struggle to perceive tools in realistic scenes, and the much larger drop at the planning stage further indicates a lack of functional commonsense for mapping perceived tools onto task semantics, pinpointing a critical bottleneck for the development of practical embodied AI.

Large Language Models (LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (Gemini 3.1 Pro, Claude 4.6 Opus, GPT 5.4) corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely. Additional experiments reveal that agentic tool use does not improve performance on DELEGATE-52, and that degradation severity is exacerbated by document size, length of interaction, or presence of distractor files. Our analysis shows that current LLMs are unreliable delegates: they introduce sparse but severe errors that silently corrupt documents, compounding over long interaction.

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of Large Language Models (LLMs). However, these methods often suffer from overthinking, leading to unnecessarily lengthy or redundant reasoning traces. Existing approaches attempt to mitigate this issue through curating multiple reasoning chains for training LLMs, but their effectiveness is often constrained by the quality of the generated data and prone to overfitting. To address the challenge, we propose Reasoning Compression ThroUgh Stepwise Trials (ReCUT), a novel method aimed at balancing the accuracy and length of reasoning trajectory. Specifically, ReCUT employs a stepwise exploration mechanism and a long-short switched sampling strategy, enabling LLMs to incrementally generate diverse reasoning paths. These paths are evaluated and used to construct preference pairs to train two specialized models (Gemini LLMs)-one optimized for reasoning accuracy, the other for shorter reasoning. A final integrated model is obtained by interpolating the parameters of these two models. Experimental results across multiple math reasoning datasets and backbone models demonstrate that ReCUT significantly reduces reasoning lengths by approximately 30-50%, while maintaining or improving reasoning accuracy compared to various baselines. All codes and data will be released via https://github.com/NEUIR/ReCUT.

Multimodal large language models (MLLMs) have made rapid progress in recent years, yet continue to struggle with low-level visual perception (LLVP) -- particularly the ability to accurately describe the geometric details of an image. This capability is crucial for applications in areas such as robotics, medical image analysis, and manufacturing. In this paper, we first introduce Geoperception, a benchmark designed to evaluate an MLLM's ability to accurately transcribe 2D geometric information from an image. Using this benchmark, we demonstrate the limitations of leading MLLMs, and then conduct a comprehensive empirical study to explore strategies for improving their performance on geometric tasks. Our findings highlight the benefits of certain model architectures, training techniques, and data strategies, including the use of high-fidelity synthetic data and multi-stage training with a data curriculum. Notably, we find that a data curriculum enables models to learn challenging geometry understanding tasks which they fail to learn from scratch. Leveraging these insights, we develop Euclid, a family of models specifically optimized for strong low-level geometric perception. Although purely trained on synthetic multimodal data, Euclid shows strong generalization ability to novel geometry shapes. For instance, Euclid outperforms the best closed-source model, Gemini-1.5-Pro, by up to 58.56% on certain Geoperception benchmark tasks and 10.65% on average across all tasks.

Humans build shared spatial understanding by communicating partial, viewpoint-dependent observations. We ask whether Multimodal Large Language Models (MLLMs) can do the same, aligning distinct egocentric views through dialogue to form a coherent, allocentric mental model of a shared environment. To study this systematically, we introduce COSMIC, a benchmark for Collaborative Spatial Communication. In this setting, two static MLLM agents observe a 3D indoor environment from different viewpoints and exchange natural-language messages to solve spatial queries. COSMIC contains 899 diverse scenes and 1250 question-answer pairs spanning five tasks. We find a consistent capability hierarchy, MLLMs are most reliable at identifying shared anchor objects across views, perform worse on relational reasoning, and largely fail at building globally consistent maps, performing near chance, even for the frontier models. Moreover, we find thinking capability yields consistent gains in anchor grounding, but is insufficient for higher-level spatial communication. To contextualize model behavior, we additionally collect 250 human-human dialogues. Humans achieve 95% aggregate accuracy, leaving significant room for improvement for even the best performing model Gemini-3-Pro-Thinking which achieves 72% aggregate accuracy. Moreover, human conversations become increasingly specific as partners converge on a shared mental model, whereas model dialogues continue to explore new possibilities rather than converging, consistent with a limited ability to build and maintain a robust shared mental model. Our code and data is available at https://github.com/ankursikarwar/Cosmic

We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, tracking), visual reasoning (spatial, temporal, predictive, causal, counterfactual), and navigation (room-to-room, object retrieval) tasks. HourVideo includes 500 manually curated egocentric videos from the Ego4D dataset, spanning durations of 20 to 120 minutes, and features 12,976 high-quality, five-way multiple-choice questions. Benchmarking results reveal that multimodal models, including GPT-4 and LLaVA-NeXT, achieve marginal improvements over random chance. In stark contrast, human experts significantly outperform the state-of-the-art long-context multimodal model, Gemini Pro 1.5 (85.0% vs. 37.3%), highlighting a substantial gap in multimodal capabilities. Our benchmark, evaluation toolkit, prompts, and documentation are available at https://hourvideo.stanford.edu

By leveraging tool-augmented Multimodal Large Language Models (MLLMs), multi-agent frameworks are driving progress in video understanding. However, most of them adopt static and non-learnable tool invocation mechanisms, which limit the discovery of diverse clues essential for robust perception and reasoning regarding temporally or spatially complex videos. To address this challenge, we propose a novel Multi-agent system for video understanding, namely VideoChat-M1. Instead of using a single or fixed policy, VideoChat-M1 adopts a distinct Collaborative Policy Planning (CPP) paradigm with multiple policy agents, which comprises three key processes. (1) Policy Generation: Each agent generates its unique tool invocation policy tailored to the user's query; (2) Policy Execution: Each agent sequentially invokes relevant tools to execute its policy and explore the video content; (3) Policy Communication: During the intermediate stages of policy execution, agents interact with one another to update their respective policies. Through this collaborative framework, all agents work in tandem, dynamically refining their preferred policies based on contextual insights from peers to effectively respond to the user's query. Moreover, we equip our CPP paradigm with a concise Multi-Agent Reinforcement Learning (MARL) method. Consequently, the team of policy agents can be jointly optimized to enhance VideoChat-M1's performance, guided by both the final answer reward and intermediate collaborative process feedback. Extensive experiments demonstrate that VideoChat-M1 achieves SOTA performance across eight benchmarks spanning four tasks. Notably, on LongVideoBench, our method outperforms the SOTA model Gemini 2.5 pro by 3.6% and GPT-4o by 15.6%.

Finetuning provides a scalable and cost-effective means of customizing language models for specific tasks or response styles, with greater reliability than prompting or in-context learning. In contrast, the conventional wisdom is that injecting knowledge via finetuning results in brittle performance and poor generalization. We argue that the dichotomy of "task customization" (e.g., instruction tuning) and "knowledge injection" (e.g., teaching new facts) is a distinction without a difference. We instead identify concrete factors that explain the heterogeneous effectiveness observed with finetuning. To this end, we conduct a large-scale experimental study of finetuning the frontier Gemini v1.5 model family on a spectrum of datasets that are artificially engineered to interpolate between the strengths and failure modes of finetuning. Our findings indicate that question-answer training data formats provide much stronger knowledge generalization than document/article-style training data, numerical information can be harder for finetuning to retain than categorical information, and models struggle to apply finetuned knowledge during multi-step reasoning even when trained on similar examples -- all factors that render "knowledge injection" to be especially difficult, even after controlling for considerations like data augmentation and information volume. On the other hand, our findings also indicate that it is not fundamentally more difficult to finetune information about a real-world event than information about what a model's writing style should be.

Islamic inheritance ___domain holds significant importance for Muslims to ensure fair distribution of shares between heirs. Manual calculation of shares under numerous scenarios is complex, time-consuming, and error-prone. Recent advancements in Large Language Models (LLMs) have sparked interest in their potential to assist with complex legal reasoning tasks. This study evaluates the reasoning capabilities of state-of-the-art LLMs to interpret and apply Islamic inheritance laws. We utilized the dataset proposed in the ArabicNLP QIAS 2025 challenge, which includes inheritance case scenarios given in Arabic and derived from Islamic legal sources. Various base and fine-tuned models, are assessed on their ability to accurately identify heirs, compute shares, and justify their reasoning in alignment with Islamic legal principles. Our analysis reveals that the proposed majority voting solution, leveraging three base models (Gemini Flash 2.5, Gemini Pro 2.5, and GPT o3), outperforms all other models that we utilized across every difficulty level. It achieves up to 92.7% accuracy and secures the third place overall in Task 1 of the Qias 2025 challenge.

We present and evaluate a suite of proof-of-concept (PoC), structured workflow prompts designed to elicit human-like hierarchical reasoning while guiding Large Language Models (LLMs) in the high-level semantic and linguistic analysis of scholarly manuscripts. The prompts target two non-trivial analytical tasks within academic summaries (abstracts and conclusions): identifying unsubstantiated claims (informational integrity) and flagging semantically confusing ambiguous pronoun references (linguistic clarity). We conducted a systematic, multi-run evaluation on two frontier models (Gemini Pro 2.5 Pro and ChatGPT Plus o3) under varied context conditions. Our results for the informational integrity task reveal a significant divergence in model performance: while both models successfully identified an unsubstantiated head of a noun phrase (95% success), ChatGPT consistently failed (0% success) to identify an unsubstantiated adjectival modifier that Gemini correctly flagged (95% success), raising a question regarding the potential influence of the target's syntactic role. For the linguistic analysis task, both models performed well (80-90% success) with full manuscript context. Surprisingly, in a summary-only setting, Gemini's performance was substantially degraded, while ChatGPT achieved a perfect (100%) success rate. Our findings suggest that while structured prompting is a viable methodology for complex textual analysis, prompt performance may be highly dependent on the interplay between the model, task type, and context, highlighting the need for rigorous, model-specific testing.

With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other languages benefits from large datasets and well-established benchmarks, Arabic OCR faces unique challenges due to its cursive script, right-to-left text flow, and complex typographic and calligraphic features. We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems. Our benchmark comprises 8,809 samples across 9 major domains and 36 sub-domains, encompassing diverse document types including handwritten text, structured tables, and specialized coverage of 21 chart types for business intelligence. Our findings show that modern vision-language models (such as GPT-4, Gemini, and Qwen) outperform traditional OCR approaches (like EasyOCR, PaddleOCR, and Surya) by an average of 60% in Character Error Rate (CER). Furthermore, we highlight significant limitations of current Arabic OCR models, particularly in PDF-to-Markdown conversion, where the best model Gemini-2.0-Flash achieves only 65% accuracy. This underscores the challenges in accurately recognizing Arabic text, including issues with complex fonts, numeral recognition errors, word elongation, and table structure detection. This work establishes a rigorous evaluation framework that can drive improvements in Arabic document analysis methods and bridge the performance gap with English OCR technologies.

Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams, whereas existing benchmarks largely fail to evaluate this capability. They restrict videos to short clips, isolate modalities, or reduce questions to one-hop perception. We introduce TraceAV-Bench, the first benchmark to jointly evaluate multi-hop reasoning over long audio-visual trajectories and multimodal hallucination robustness. TraceAV-Bench comprises 2,200 rigorously validated multiple-choice questions over 578 long videos, totaling 339.5 hours, spanning 4 evaluation dimensions and 15 sub-tasks. Each question is grounded in an explicit reasoning chain that averages 3.68 hops across a 15.1-minute temporal span. The dataset is built by a three-step semi-automated pipeline followed by a strict quality assurance process. Evaluation of multiple representative OmniLLMs on TraceAV-Bench reveals that the benchmark poses a persistent challenge across all models, with the strongest closed-source model (Gemini 3.1 Pro) reaching only 68.29% on general tasks, and the best open-source model (Ming-Flash-Omni-2.0) reaching 51.70%, leaving substantial headroom. Moreover, we find that robustness to multimodal hallucination is largely decoupled from general multimodal reasoning performance. We anticipate that TraceAV-Bench will stimulate further research toward OmniLLMs that can reason coherently and faithfully over long-form audio-visual content.

While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, visuospatial cognition - reasoning about spatial layouts, relations, and dynamics - remains a significant challenge. Existing models often lack the necessary architectural components and specialized training data for fine-grained spatial understanding. We introduce ViCA2 (Visuospatial Cognitive Assistant 2), a novel MLLM designed to enhance spatial reasoning. ViCA2 features a dual vision encoder architecture integrating SigLIP for semantics and Hiera for spatial structure, coupled with a token ratio control mechanism for efficiency. We also developed ViCA-322K, a new large-scale dataset with over 322,000 spatially grounded question-answer pairs for targeted instruction tuning. On the challenging VSI-Bench benchmark, our ViCA2-7B model achieves a state-of-the-art average score of 56.8, significantly surpassing larger open-source models (e.g., LLaVA-NeXT-Video-72B, 40.9) and leading proprietary models (Gemini-1.5 Pro, 45.4). This demonstrates the effectiveness of our approach in achieving strong visuospatial intelligence with a compact model. We release ViCA2, its codebase, and the ViCA-322K dataset to facilitate further research.

Large Multimodal Models (LMMs) are increasingly applied to scientific research, yet it remains unclear whether they can reliably understand and reason over the multimodal complexity of papers. A central challenge lies in detecting and resolving inconsistencies across text, figures, tables, and equations, issues that are often subtle, ___domain-specific, and ultimately undermine clarity, reproducibility, and trust. Existing benchmarks overlook this issue, either isolating single modalities or relying on synthetic errors that fail to capture real-world complexity. We introduce PRISMM-Bench (Peer-Review-sourced Inconsistency Set for Multimodal Models), the first benchmark grounded in real reviewer-flagged inconsistencies in scientific papers. Through a multi-stage pipeline of review mining, LLM-assisted filtering and human verification, we curate 262 inconsistencies from 242 papers. Based on this set, we design three tasks, namely inconsistency identification, remedy and pair matching, which assess a model's capacity to detect, correct, and reason over inconsistencies across different modalities. Furthermore, to address the notorious problem of choice-only shortcuts in multiple-choice evaluation, where models exploit answer patterns without truly understanding the question, we further introduce structured JSON-based answer representations that minimize linguistic biases by reducing reliance on superficial stylistic cues. We benchmark 21 leading LMMs, including large open-weight models (GLM-4.5V 106B, InternVL3 78B) and proprietary models (Gemini 2.5 Pro, GPT-5 with high reasoning). Results reveal strikingly low performance (26.1-54.2%), underscoring the challenge of multimodal scientific reasoning and motivating progress towards trustworthy scientific assistants.

Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, their efficacy in video OCR is significantly diminished due to factors such as motion blur, temporal variations, and visual effects inherent in video content. To provide clearer guidance for training practical MLLMs, we introduce the MME-VideoOCR benchmark, which encompasses a comprehensive range of video OCR application scenarios. MME-VideoOCR features 10 task categories comprising 25 individual tasks and spans 44 diverse scenarios. These tasks extend beyond text recognition to incorporate deeper comprehension and reasoning of textual content within videos. The benchmark consists of 1,464 videos with varying resolutions, aspect ratios, and durations, along with 2,000 meticulously curated, manually annotated question-answer pairs. We evaluate 18 state-of-the-art MLLMs on MME-VideoOCR, revealing that even the best-performing model (Gemini-2.5 Pro) achieves an accuracy of only 73.7%. Fine-grained analysis indicates that while existing MLLMs demonstrate strong performance on tasks where relevant texts are contained within a single or few frames, they exhibit limited capability in effectively handling tasks that demand holistic video comprehension. These limitations are especially evident in scenarios that require spatio-temporal reasoning, cross-frame information integration, or resistance to language prior bias. Our findings also highlight the importance of high-resolution visual input and sufficient temporal coverage for reliable OCR in dynamic video scenarios.

Metaphorical comprehension in images remains a critical challenge for Nowadays AI systems. While Multimodal Large Language Models (MLLMs) excel at basic Visual Question Answering (VQA), they consistently struggle to grasp the nuanced cultural, emotional, and contextual implications embedded in visual content. This difficulty stems from the task's demand for sophisticated multi-hop reasoning, cultural context, and Theory of Mind (ToM) capabilities, which current models lack. To fill this gap, we propose MetaphorStar, the first end-to-end visual reinforcement learning (RL) framework for image implication tasks. Our framework includes three core components: the fine-grained dataset TFQ-Data, the visual RL method TFQ-GRPO, and the well-structured benchmark TFQ-Bench. Our fully open-source MetaphorStar family, trained using TFQ-GRPO on TFQ-Data, significantly improves performance by an average of 82.6% on the image implication benchmarks. Compared with 20+ mainstream MLLMs, MetaphorStar-32B achieves state-of-the-art (SOTA) on Multiple-Choice Question and Open-Style Question, significantly outperforms the top closed-source model Gemini-3.0-pro on True-False Question. Crucially, our experiments reveal that learning image implication tasks improves the general understanding ability, especially the complex visual reasoning ability. We further provide a systematic analysis of model parameter scaling, training data scaling, and the impact of different model architectures and training strategies, demonstrating the broad applicability of our method. We open-sourced all model weights, datasets, and method code at https://metaphorstar.github.io.

Large language models (LLMs) excel in natural language generation but often confidently produce incorrect responses, especially in tasks like mathematical reasoning. Chain-of-thought prompting, self-verification, and multi-agent debate are among the strategies proposed to improve the reasoning and factual accuracy of LLMs. Building on Du et al.'s multi-agent debate framework, we find that multi-agent debate helps at any model scale, and that diversity of thought elicits stronger reasoning in debating LLMs. Across various model sizes, performance on mathematical reasoning tasks benefits most when diverse trained models are used. Remarkably, after 4 rounds of debate, a diverse set of medium-capacity models (Gemini-Pro, Mixtral 7BX8, and PaLM 2-M) outperforms GPT-4 on the GSM-8K benchmark, scoring 91% accuracy. By comparison, when 3 instances of Gemini-Pro are used, performance only reaches 82%. Finally, this diverse set of medium-capacity models sets a new state-of-the-art performance on the ASDiv benchmark (94%). These results underscore the idea that the future of AI is agentic, with diverse cooperating agents yielding emergent capabilities beyond even the most powerful individual models.

Large language models (LLMs) have exhibited the ability to effectively utilize external tools to address user queries. However, their performance may be limited in complex, multi-turn interactions involving users and multiple tools. To address this, we propose Magnet, a principled framework for synthesizing high-quality training trajectories to enhance the function calling capability of large language model agents in multi-turn conversations with humans. The framework is based on automatic and iterative translations from a function signature path to a sequence of queries and executable function calls. We model the complicated function interactions in multi-turn cases with graph and design novel node operations to build reliable signature paths. Motivated by context distillation, when guiding the generation of positive and negative trajectories using a teacher model, we provide reference function call sequences as positive hints in context and contrastive, incorrect function calls as negative hints. Experiments show that training with the positive trajectories with supervised fine-tuning and preference optimization against negative trajectories, our 14B model, Magnet-14B-mDPO, obtains 68.01 on BFCL-v3 and 73.30 on ToolQuery, surpassing the performance of the teacher model Gemini-1.5-pro-002 by a large margin in function calling.

We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage the multimodal capabilities of Gemini to produce embeddings for arbitrary combinations of interleaved inputs across all these modalities that generalize well across a wide variety of tasks. Applying large-scale contrastive learning in a multi-task multi-stage training setup, we achieve state-of-the-art performance on key embedding benchmarks including unimodal, cross-modal, and multimodal retrieval spanning a diverse set of tasks. We show that our embedding model demonstrates strong performance (with a score of 62.9 R@1 on MSCOCO, 68.8 NDCG@10 on Vatex, 69.9 on MTEB multilingual and 84.0 on MTEB Code) across a variety of tasks surpassing the performance of specialized models. These unified capabilities make Gemini Embedding 2 a promising candidate for downstream use cases such as RAG, recommendation and search. Furthermore, its robust zero-shot performance across distinct fields - from astronomy and bioscience to fine arts and the culinary arts - establishes it as a highly reliable, out-of-the-box representation even for specialized domains.

We benchmark how internal reasoning traces, which we call thought streams, affect video scene understanding in vision-language models. Using four configurations of Google's Gemini 2.5 Flash and Flash Lite across scenes extracted from 100 hours of video, we ask three questions: does more thinking lead to better outputs, where do the gains stop, and what do these models actually think about? We introduce three evaluation metrics. Contentfulness measures how much of the thought stream is useful scene content versus meta-commentary. Thought-Final Coverage measures how faithfully the thought stream translates into the final output. Dominant Entity Analysis identifies which subjects, actions, and settings the model focuses on. GPT-5 serves as an independent judge. We find that quality gains from additional thinking plateau quickly, with most improvement occurring in the first few hundred tokens. Flash Lite offers the best balance between quality and token usage. Tight reasoning budgets cause the model to add content in the final output that it never reasoned about, a form of compression-step hallucination. Despite being different model tiers, Flash and Flash Lite produce similar thought streams, though they differ in style: Flash discusses its reasoning process, while Lite focuses on describing the scene.

AI models are increasingly used for data analysis and visualization, yet benchmarks rarely address scatterplot-specific tasks, limiting insight into performance. To address this gap for one of the most common chart types, we introduce a synthetic, annotated dataset of over 18,000 scatterplots from six data generators and 17 chart designs, and a benchmark based on it. We evaluate proprietary models from OpenAI and Google using N-shot prompting on five distinct tasks derived from annotations of cluster bounding boxes, their center coordinates, and outlier coordinates. OpenAI models and Gemini 2.5 Flash, especially when prompted with examples, are viable options for counting clusters and, in Flash's case, outliers (90%+ Accuracy). However, the results for localization-related tasks are unsatisfactory: Precision and Recall are near or below 50%, except for Flash in outlier identification (65.01%). Furthermore, the impact of chart design on performance appears to be a secondary factor, but it is advisable to avoid scatterplots with wide aspect ratios (16:9 and 21:9) or those colored randomly. Supplementary materials are available at https://github.com/feedzai/biy-paper.

Many clinical tasks require an understanding of specialized data, such as medical images and genomics, which is not typically found in general-purpose large multimodal models. Building upon Gemini's multimodal models, we develop several models within the new Med-Gemini family that inherit core capabilities of Gemini and are optimized for medical use via fine-tuning with 2D and 3D radiology, histopathology, ophthalmology, dermatology and genomic data. Med-Gemini-2D sets a new standard for AI-based chest X-ray (CXR) report generation based on expert evaluation, exceeding previous best results across two separate datasets by an absolute margin of 1% and 12%, where 57% and 96% of AI reports on normal cases, and 43% and 65% on abnormal cases, are evaluated as "equivalent or better" than the original radiologists' reports. We demonstrate the first ever large multimodal model-based report generation for 3D computed tomography (CT) volumes using Med-Gemini-3D, with 53% of AI reports considered clinically acceptable, although additional research is needed to meet expert radiologist reporting quality. Beyond report generation, Med-Gemini-2D surpasses the previous best performance in CXR visual question answering (VQA) and performs well in CXR classification and radiology VQA, exceeding SoTA or baselines on 17 of 20 tasks. In histopathology, ophthalmology, and dermatology image classification, Med-Gemini-2D surpasses baselines across 18 out of 20 tasks and approaches task-specific model performance. Beyond imaging, Med-Gemini-Polygenic outperforms the standard linear polygenic risk score-based approach for disease risk prediction and generalizes to genetically correlated diseases for which it has never been trained. Although further development and evaluation are necessary in the safety-critical medical ___domain, our results highlight the potential of Med-Gemini across a wide range of medical tasks.

In this report, we introduce Gemini Embedding, a state-of-the-art embedding model leveraging the power of Gemini, Google's most capable large language model. Capitalizing on Gemini's inherent multilingual and code understanding capabilities, Gemini Embedding produces highly generalizable embeddings for text spanning numerous languages and textual modalities. The representations generated by Gemini Embedding can be precomputed and applied to a variety of downstream tasks including classification, similarity, clustering, ranking, and retrieval. Evaluated on the Massive Multilingual Text Embedding Benchmark (MMTEB), which includes over one hundred tasks across 250+ languages, Gemini Embedding substantially outperforms prior state-of-the-art models, demonstrating considerable improvements in embedding quality. Achieving state-of-the-art performance across MMTEB's multilingual, English, and code benchmarks, our unified model demonstrates strong capabilities across a broad selection of tasks and surpasses specialized ___domain-specific models.

Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as robots remains a significant challenge. This report introduces a new family of AI models purposefully designed for robotics and built upon the foundation of Gemini 2.0. We present Gemini Robotics, an advanced Vision-Language-Action (VLA) generalist model capable of directly controlling robots. Gemini Robotics executes smooth and reactive movements to tackle a wide range of complex manipulation tasks while also being robust to variations in object types and positions, handling unseen environments as well as following diverse, open vocabulary instructions. We show that with additional fine-tuning, Gemini Robotics can be specialized to new capabilities including solving long-horizon, highly dexterous tasks, learning new short-horizon tasks from as few as 100 demonstrations and adapting to completely novel robot embodiments. This is made possible because Gemini Robotics builds on top of the Gemini Robotics-ER model, the second model we introduce in this work. Gemini Robotics-ER (Embodied Reasoning) extends Gemini's multimodal reasoning capabilities into the physical world, with enhanced spatial and temporal understanding. This enables capabilities relevant to robotics including object detection, pointing, trajectory and grasp prediction, as well as multi-view correspondence and 3D bounding box predictions. We show how this novel combination can support a variety of robotics applications. We also discuss and address important safety considerations related to this new class of robotics foundation models. The Gemini Robotics family marks a substantial step towards developing general-purpose robots that realizes AI's potential in the physical world.

While generalist foundation models like Gemini and GPT-4o demonstrate impressive multi-modal competence, existing evaluations fail to test their intelligence in dynamic, interactive worlds. Static benchmarks lack agency, while interactive benchmarks suffer from a severe modal bottleneck, typically ignoring crucial auditory and temporal cues. To bridge this evaluation chasm, we introduce OmniPlay, a diagnostic benchmark designed not just to evaluate, but to probe the fusion and reasoning capabilities of agentic models across the full sensory spectrum. Built on a core philosophy of modality interdependence, OmniPlay comprises a suite of five game environments that systematically create scenarios of both synergy and conflict, forcing agents to perform genuine cross-modal reasoning. Our comprehensive evaluation of six leading omni-modal models reveals a critical dichotomy: they exhibit superhuman performance on high-fidelity memory tasks but suffer from systemic failures in challenges requiring robust reasoning and strategic planning. We demonstrate that this fragility stems from brittle fusion mechanisms, which lead to catastrophic performance degradation under modality conflict and uncover a counter-intuitive "less is more" paradox, where removing sensory information can paradoxically improve performance. Our findings suggest that the path toward robust AGI requires a research focus beyond scaling to explicitly address synergistic fusion. Our platform is available for anonymous review at https://github.com/fuqingbie/omni-game-benchmark.

Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT-4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE). SAFE utilizes an LLM to break down a long-form response into a set of individual facts and to evaluate the accuracy of each fact using a multi-step reasoning process comprising sending search queries to Google Search and determining whether a fact is supported by the search results. Furthermore, we propose extending F1 score as an aggregated metric for long-form factuality. To do so, we balance the percentage of supported facts in a response (precision) with the percentage of provided facts relative to a hyperparameter representing a user's preferred response length (recall). Empirically, we demonstrate that LLM agents can achieve superhuman rating performance - on a set of ~16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time. At the same time, SAFE is more than 20 times cheaper than human annotators. We also benchmark thirteen language models on LongFact across four model families (Gemini, GPT, Claude, and PaLM-2), finding that larger language models generally achieve better long-form factuality. LongFact, SAFE, and all experimental code are available at https://github.com/google-deepmind/long-form-factuality.

Large Language Models (LLMs) for code are rapidly evolving, with code editing emerging as a critical capability. We introduce CodeEditorBench, an evaluation framework designed to rigorously assess the performance of LLMs in code editing tasks, including debugging, translating, polishing, and requirement switching. Unlike existing benchmarks focusing solely on code generation, CodeEditorBench emphasizes real-world scenarios and practical aspects of software development. We curate diverse coding challenges and scenarios from five sources, covering various programming languages, complexity levels, and editing tasks. Evaluation of 19 LLMs reveals that closed-source models (particularly Gemini-Ultra and GPT-4), outperform open-source models in CodeEditorBench, highlighting differences in model performance based on problem types and prompt sensitivities. CodeEditorBench aims to catalyze advancements in LLMs by providing a robust platform for assessing code editing capabilities. We will release all prompts and datasets to enable the community to expand the dataset and benchmark emerging LLMs. By introducing CodeEditorBench, we contribute to the advancement of LLMs in code editing and provide a valuable resource for researchers and practitioners.

Generative AI has made remarkable strides to revolutionize fields such as image and video generation. These advancements are driven by innovative algorithms, architecture, and data. However, the rapid proliferation of generative models has highlighted a critical gap: the absence of trustworthy evaluation metrics. Current automatic assessments such as FID, CLIP, FVD, etc often fail to capture the nuanced quality and user satisfaction associated with generative outputs. This paper proposes an open platform GenAI-Arena to evaluate different image and video generative models, where users can actively participate in evaluating these models. By leveraging collective user feedback and votes, GenAI-Arena aims to provide a more democratic and accurate measure of model performance. It covers three arenas for text-to-image generation, text-to-video generation, and image editing respectively. Currently, we cover a total of 27 open-source generative models. GenAI-Arena has been operating for four months, amassing over 6000 votes from the community. We describe our platform, analyze the data, and explain the statistical methods for ranking the models. To further promote the research in building model-based evaluation metrics, we release a cleaned version of our preference data for the three tasks, namely GenAI-Bench. We prompt the existing multi-modal models like Gemini, GPT-4o to mimic human voting. We compute the correlation between model voting with human voting to understand their judging abilities. Our results show existing multimodal models are still lagging in assessing the generated visual content, even the best model GPT-4o only achieves a Pearson correlation of 0.22 in the quality subscore, and behaves like random guessing in others.

Speech quality assessment typically requires evaluating audio from multiple aspects, such as mean opinion score (MOS) and speaker similarity (SIM) \etc., which can be challenging to cover using one small model designed for a single task. In this paper, we propose leveraging recently introduced auditory large language models (LLMs) for automatic speech quality assessment. By employing task-specific prompts, auditory LLMs are finetuned to predict MOS, SIM and A/B testing results, which are commonly used for evaluating text-to-speech systems. Additionally, the finetuned auditory LLM is able to generate natural language descriptions assessing aspects like noisiness, distortion, discontinuity, and overall quality, providing more interpretable outputs. Extensive experiments have been performed on the NISQA, BVCC, SOMOS and VoxSim speech quality datasets, using open-source auditory LLMs such as SALMONN, Qwen-Audio, and Qwen2-Audio. For the natural language descriptions task, a commercial model Google Gemini 1.5 Pro is also evaluated. The results demonstrate that auditory LLMs achieve competitive performance compared to state-of-the-art task-specific small models in predicting MOS and SIM, while also delivering promising results in A/B testing and natural language descriptions. Our data processing scripts and finetuned model checkpoints can be found at https://github.com/bytedance/SALMONN.

Recent advancements in Unified Multimodal Models (UMMs) have enabled remarkable image understanding and generation capabilities. However, while models like Gemini-2.5-Flash-Image show emerging abilities to reason over multiple related images, existing benchmarks rarely address the challenges of multi-image context generation, focusing mainly on text-to-image or single-image editing tasks. In this work, we introduce MICON-Bench, a comprehensive benchmark covering six tasks that evaluate cross-image composition, contextual reasoning, and identity preservation. We further propose an MLLM-driven Evaluation-by-Checkpoint framework for automatic verification of semantic and visual consistency, where multimodal large language model (MLLM) serves as a verifier. Additionally, we present Dynamic Attention Rebalancing (DAR), a training-free, plug-and-play mechanism that dynamically adjusts attention during inference to enhance coherence and reduce hallucinations. Extensive experiments on various state-of-the-art open-source models demonstrate both the rigor of MICON-Bench in exposing multi-image reasoning challenges and the efficacy of DAR in improving generation quality and cross-image coherence. Github: https://github.com/Angusliuuu/MICON-Bench.

Web agents require massive trajectories to generalize, yet real-world training is constrained by network latency, rate limits, and safety risks. We introduce WebWorld series, the first open-web simulator trained at scale. While existing simulators are restricted to closed environments with thousands of trajectories, WebWorld leverages a scalable data pipeline to train on 1M+ open-web interactions, supporting reasoning, multi-format data, and long-horizon simulations of 30+ steps. For intrinsic evaluation, we introduce WebWorld-Bench with dual metrics spanning nine dimensions, where WebWorld achieves simulation performance comparable to Gemini-3-Pro. For extrinsic evaluation, Qwen3-14B trained on WebWorld-synthesized trajectories improves by +9.2\% on WebArena, reaching performance comparable to GPT-4o. WebWorld enables effective inference-time search, outperforming GPT-5 as a world model. Beyond web simulation, WebWorld exhibits cross-___domain generalization to code, GUI, and game environments, providing a replicable recipe for world model construction.

Proprietary AI systems have recently demonstrated impressive capabilities on complex proof-based problems, with gold-level performance reported at the 2025 International Mathematical Olympiad (IMO). However, the training pipelines behind these systems remain largely undisclosed, and their reliance on large "internal" models and scaffolds makes them expensive to run, difficult to reproduce, and hard to study or improve upon. This raises a central question: can small, open models also be trained to achieve competitive reasoning performance on difficult Olympiad-level math? In this paper, we answer this question by building QED-Nano, a 4B model post-trained for Olympiad-level proofs. Our training recipe has three stages: (1) supervised fine-tuning to imbue good proof-writing styles by distilling from DeepSeek-Math-V2, (2) reinforcement learning (RL) with rubric-based rewards, and (3) expanding RL with a reasoning cache, which decomposes long proofs into iterative summarize-and-refine cycles and enables stronger test-time reasoning. QED-Nano surpasses the proof-generation performance of much larger open models, including Nomos-1 and GPT-OSS-120B, and approaches the performance of proprietary models like Gemini 3 Pro, at a fraction of the inference cost. To support further research on open mathematical reasoning, we release the full QED-Nano pipeline, including the QED-Nano and QED-Nano-SFT models, the FineProofs-SFT and FineProofs-RL datasets, and the training and evaluation code.

Generalist vision language models (VLMs) have made significant strides in computer vision, but they fall short in specialized fields like healthcare, where expert knowledge is essential. In traditional computer vision tasks, creative or approximate answers may be acceptable, but in healthcare, precision is paramount.Current large multimodal models like Gemini and GPT-4o are insufficient for medical tasks due to their reliance on memorized internet knowledge rather than the nuanced expertise required in healthcare. VLMs are usually trained in three stages: vision pre-training, vision-language pre-training, and instruction fine-tuning (IFT). IFT has been typically applied using a mixture of generic and healthcare data. In contrast, we propose that for medical VLMs, a fourth stage of specialized IFT is necessary, which focuses on medical data and includes information from ___domain expert models. Domain expert models developed for medical use are crucial because they are specifically trained for certain clinical tasks, e.g. to detect tumors and classify abnormalities through segmentation and classification, which learn fine-grained features of medical data-features that are often too intricate for a VLM to capture effectively especially in radiology. This paper introduces a new framework, VILA-M3, for medical VLMs that utilizes ___domain knowledge via expert models. Through our experiments, we show an improved state-of-the-art (SOTA) performance with an average improvement of ~9% over the prior SOTA model Med-Gemini and ~6% over models trained on the specific tasks. Our approach emphasizes the importance of ___domain expertise in creating precise, reliable VLMs for medical applications.

As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mamba's long-sequence processing efficiency with Transformer's superior contextual understanding. Hunyuan-TurboS features an adaptive long-short chain-of-thought (CoT) mechanism, dynamically switching between rapid responses for simple queries and deep "thinking" modes for complex problems, optimizing computational resources. Architecturally, this 56B activated (560B total) parameter model employs 128 layers (Mamba2, Attention, FFN) with an innovative AMF/MF block pattern. Faster Mamba2 ensures linear complexity, Grouped-Query Attention minimizes KV cache, and FFNs use an MoE structure. Pre-trained on 16T high-quality tokens, it supports a 256K context length and is the first industry-deployed large-scale Mamba model. Our comprehensive post-training strategy enhances capabilities via Supervised Fine-Tuning (3M instructions), a novel Adaptive Long-short CoT Fusion method, Multi-round Deliberation Learning for iterative improvement, and a two-stage Large-scale Reinforcement Learning process targeting STEM and general instruction-following. Evaluations show strong performance: overall top 7 rank on LMSYS Chatbot Arena with a score of 1356, outperforming leading models like Gemini-2.0-Flash-001 (1352) and o4-mini-2025-04-16 (1345). TurboS also achieves an average of 77.9% across 23 automated benchmarks. Hunyuan-TurboS balances high performance and efficiency, offering substantial capabilities at lower inference costs than many reasoning models, establishing a new paradigm for efficient large-scale pre-trained models.

Multimodal Large Language Models (MLLMs) are renowned for their superior instruction-following and reasoning capabilities across diverse problem domains. However, existing benchmarks primarily focus on assessing factual and logical correctness in downstream tasks, with limited emphasis on evaluating MLLMs' ability to interpret pragmatic cues and intermodal relationships. To address this gap, we assess the competency of MLLMs in performing Multimodal Discourse Analysis (MDA) using Coherence Relations. Our benchmark, CORDIAL, encompasses a broad spectrum of Coherence Relations across 3 different discourse domains at varying levels of granularity. Through our experiments on 10+ MLLMs employing different prompting strategies, we show that even top models like Gemini 1.5 Pro and GPT-4o fail to match the performance of simple classifier-based baselines. This study emphasizes the need to move beyond similarity-based metrics and adopt a discourse-driven framework for evaluating MLLMs, providing a more nuanced assessment of their capabilities. The benchmark and code are available at: https://github.com/aashish2000/CORDIAL.

We introduce Embodied-R1.5, a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities, spanning embodied cognition, task planning, correction, and pointing, within a single architecture toward general physical intelligence. Leveraging three automated data construction pipelines to significantly expand the data coverage of critical capabilities, we build a large-scale data system of over 15B tokens, and design a multi-task balanced RL recipe to alleviate heterogeneous task conflicts. We further introduce a Planner-Grounder-Corrector (PGC) closed-loop framework that enables a single model to autonomously execute and self-correct over long-horizon tasks. With only 8B parameters, Embodied-R1.5 achieves SOTA on 16 out of 24 embodied VLM benchmarks, surpassing leading models like Gemini-Robotics-ER-1.5 and GPT-5.4. Benefiting from the internalized embodied capabilities, Embodied-R1.5 can be fine-tuned into a VLA with only a small amount of data, outperforming leading VLA models like π_{0.5} across 4 popular manipulation benchmark suites. We further conduct extensive zero-shot real-robot experiments, validating performance in instruction following, affordance grounding, articulated object manipulation, and long-horizon complex tasks, demonstrating strong generalization to the physical world. We open-source model weights, datasets, training code, and EmbodiedEvalKit, an evaluation framework tailored for embodied tasks, to facilitate future research in EFMs.

Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from them, or do not disclose their training data or recipe. As a result, the open-source community lacks the foundations needed to improve on the state-of-the-art video (and image) language models. Crucially, many downstream applications require more than just high-level video understanding; they require grounding -- either by pointing or by tracking in pixels. Even proprietary models lack this capability. We present Molmo2, a new family of VLMs that are state-of-the-art among open-source models and demonstrate exceptional new capabilities in point-driven grounding in single image, multi-image, and video tasks. Our key contribution is a collection of 7 new video datasets and 2 multi-image datasets, including a dataset of highly detailed video captions for pre-training, a free-form video Q&A dataset for fine-tuning, a new object tracking dataset with complex queries, and an innovative new video pointing dataset, all collected without the use of closed VLMs. We also present a training recipe for this data utilizing an efficient packing and message-tree encoding scheme, and show bi-directional attention on vision tokens and a novel token-weight strategy improves performance. Our best-in-class 8B model outperforms others in the class of open weight and data models on short videos, counting, and captioning, and is competitive on long-videos. On video-grounding Molmo2 significantly outperforms existing open-weight models like Qwen3-VL (35.5 vs 29.6 accuracy on video counting) and surpasses proprietary models like Gemini 3 Pro on some tasks (38.4 vs 20.0 F1 on video pointing and 56.2 vs 41.1 J&F on video tracking).

The manual design of scenarios for Air Traffic Control (ATC) training is a demanding and time-consuming bottleneck that limits the diversity of simulations available to controllers. To address this, we introduce a novel, end-to-end approach, AirTrafficGen, that leverages large language models (LLMs) to automate and control the generation of complex ATC scenarios. Our method uses a purpose-built, graph-based representation to encode sector topology (including airspace geometry, routes, and fixes) into a format LLMs can process. Through rigorous benchmarking, we show that state-of-the-art models like Gemini 2.5 Pro and OpenAI o3 can generate high-traffic scenarios whilst maintaining operational realism. Our engineered prompting enables fine-grained control over interaction presence, type, and ___location. Initial findings suggest these models are also capable of iterative refinement, correcting flawed scenarios based on simple textual feedback. This approach provides a scalable alternative to manual scenario design, addressing the need for a greater volume and variety of ATC training and validation simulations. More broadly, this work showcases the potential of LLMs for complex planning in safety-critical domains.

Large Language Models (LLMs) have advanced Verilog code generation significantly, yet face challenges in data quality, reasoning capabilities, and computational efficiency. This paper presents ReasoningV, a novel model employing a hybrid reasoning strategy that integrates trained intrinsic capabilities with dynamic inference adaptation for Verilog code generation. Our framework introduces three complementary innovations: (1) ReasoningV-5K, a high-quality dataset of 5,000 functionally verified instances with reasoning paths created through multi-dimensional filtering of PyraNet samples; (2) a two-stage training approach combining parameter-efficient fine-tuning for foundational knowledge with full-parameter optimization for enhanced reasoning; and (3) an adaptive reasoning mechanism that dynamically adjusts reasoning depth based on problem complexity, reducing token consumption by up to 75\% while preserving performance. Experimental results demonstrate ReasoningV's effectiveness with a pass@1 accuracy of 57.8\% on VerilogEval-human, achieving performance competitive with leading commercial models like Gemini-2.0-flash (59.5\%) and exceeding the previous best open-source model by 10.4 percentage points. ReasoningV offers a more reliable and accessible pathway for advancing AI-driven hardware design automation, with our model, data, and code available at https://github.com/BUAA-CLab/ReasoningV.

Reward model (RM) plays a pivotal role in aligning large language model (LLM) with human preferences. As real-world applications increasingly involve long history trajectories, e.g., LLM agent, it becomes indispensable to evaluate whether a model's responses are not only high-quality but also grounded in and consistent with the provided context. Yet, current RMs remain confined to short-context settings and primarily focus on response-level attributes (e.g., safety or helpfulness), while largely neglecting the critical dimension of long context-response consistency. In this work, we introduce Long-RewardBench, a benchmark specifically designed for long-context RM evaluation, featuring both Pairwise Comparison and Best-of-N tasks. Our preliminary study reveals that even state-of-the-art generative RMs exhibit significant fragility in long-context scenarios, failing to maintain context-aware preference judgments. Motivated by the analysis of failure patterns observed in model outputs, we propose a general multi-stage training strategy that effectively scales arbitrary models into robust Long-context RMs (LongRMs). Experiments show that our approach not only substantially improves performance on long-context evaluation but also preserves strong short-context capability. Notably, our 8B LongRM outperforms much larger 70B-scale baselines and matches the performance of the proprietary Gemini 2.5 Pro model.

We investigate whether large language models produce different medical triage recommendations for identical neurological symptoms when only the patient's stated gender and age vary. Using three model families--Gemini 3.5 Flash, Claude Sonnet 4.6, and GPT-5.4-mini--we present a standardized symptom profile (persistent headache, blurred vision, morning nausea, visual disturbances) across seven demographic conditions: three age groups (25, 38, 65) x two genders (male, female), plus a gender-unspecified baseline (n = 30 per condition per model, 630 total trials). We find a stark, systemic gender-dependent triage disparity: young women receive significantly lower emergency room (ER) referral rates than age-matched men (Gemini: 0% vs. 23.3%; Claude: 6.7% vs. 96.7%; GPT: 6.7% vs. 66.7%, all p < 0.001). The disparity disappears at age 65 for all models. The primary mechanism is diagnostic substitution: the models anchor on a gender-associated diagnosis, preferentially classifying young women with Idiopathic Intracranial Hypertension (IIH)--a condition epidemiologically linked to women of childbearing age--while diagnosing men with generic increased intracranial pressure with space-occupying lesions in the differential. This diagnostic closure routes female patients to lower-urgency care (outpatient doctor appointments) despite comparable severity ratings (7-9/10). Our findings demonstrate that clinical LLMs replicate documented human clinical biases by using epidemiological priors to suppress triage urgency, suggesting that AI triage engines must decouple urgency assessment from probabilistic diagnostic priors. We release all code, prompts, and raw results.

This paper introduces a novel Deep Researcher architecture designed to generate detailed research reports on complex PhD level topics by addressing the inherent limitations of the Parallel Scaling paradigm. Our system utilizes two key innovations: Sequential Research Plan Refinement via Reflection and a Candidates Crossover algorithm. The sequential refinement process is demonstrated as an efficient method that allows the agent to maintain a centralized Global Research Context, enabling it to look back at current progress, reason about the research plan, and intelligently make changes at runtime. This dynamic adaptation contrasts with parallel approaches, which often suffer from siloed knowledge. The Candidates Crossover algorithm further enhances search efficiency by deploying multiple LLM candidates with varied parameters to explore a larger search space, with their findings synthesized to curate a comprehensive final research response. The process concludes with One Shot Report Generation, ensuring the final document is informed by a unified narrative and high fact density. Powered by the Gemini 2.5 Pro model, our Deep Researcher was evaluated on the DeepResearch Bench, a globally recognized benchmark of 100 doctoral level research tasks. Our architecture achieved an overall score of 46.21, demonstrating superior performance by surpassing leading deep research agents such as Claude Researcher, Nvidia AIQ Research Assistant, Perplexity Research, Kimi Researcher and Grok Deeper Search present on the DeepResearch Bench actively running leaderboard. This performance marginally exceeds our previous work, Static DRA, and reinforces the finding that sequential scaling consistently outperforms the parallel self consistency paradigm.

This paper presents a dynamic cryptocurrency portfolio optimization strategy that integrates technical indicators and sentiment analysis to enhance investment decision-making. The proposed method employs the 14-day Relative Strength Index (RSI) and 14-day Simple Moving Average (SMA) to capture market momentum, while sentiment scores are extracted from news articles using the VADER (Valence Aware Dictionary and sEntiment Reasoner) model, with compound scores quantifying overall market tone. The large language model Google Gemini is used to further verify the sentiment scores predicted by VADER and give investment decisions. These technical indicator and sentiment signals are incorporated into the expected return estimates before applying mean-variance optimization with constraints on asset weights. The strategy is evaluated through a rolling-window backtest over cryptocurrency market data, with Bitcoin (BTC) and an equal-weighted portfolio of selected cryptocurrencies serving as benchmarks. Experimental results show that the proposed approach achieves a cumulative return of 38.72, substantially exceeding Bitcoin's 8.85 and the equal-weighted portfolio's 21.65 over the same period, and delivers a higher Sharpe ratio (1.1093 vs. 0.8853 and 1.0194, respectively). However, the strategy exhibits a larger maximum drawdown (-18.52%) compared to Bitcoin (-4.48%) and the equal-weighted portfolio (-11.02%), indicating higher short-term downside risk. These results highlight the potential of combining sentiment and technical signals to improve cryptocurrency portfolio performance, while also emphasizing the need to address risk exposure in volatile markets.

Recent progress in large language models (LLMs) has been propelled by reinforcement learning with verifiable rewards (RLVR) and test-time scaling. However, the limited output length of LLMs constrains the depth of reasoning attainable in a single inference process. Multi-agent reasoning systems offer a promising alternative by employing multiple agents including Solver, Verifier, and Corrector, to iteratively refine solutions. While effective in closed-source models like Gemini 2.5 Pro, they struggle to generalize to open-source models due to insufficient critic and correction capabilities. To address this, we propose MarsRL, a novel reinforcement learning framework with agentic pipeline parallelism, designed to jointly optimize all agents in the system. MarsRL introduces agent-specific reward mechanisms to mitigate reward noise and employs pipeline-inspired training to enhance efficiency in handling long trajectories. Applied to Qwen3-30B-A3B-Thinking-2507, MarsRL improves AIME2025 accuracy from 86.5% to 93.3% and BeyondAIME from 64.9% to 73.8%, even surpassing Qwen3-235B-A22B-Thinking-2507. These findings highlight the potential of MarsRL to advance multi-agent reasoning systems and broaden their applicability across diverse reasoning tasks.

Large Language Models have demonstrated strong performance on many established reasoning benchmarks. However, these benchmarks primarily evaluate structured skills like quantitative problem-solving, leaving a gap in assessing flexible, multifaceted reasoning abilities that are central to human intelligence. These abilities require integrating logical deduction with spatial awareness and constraint satisfaction, which current evaluations do not measure well. To address this, we introduce RiddleBench, a benchmark of 1,737 challenging puzzles in English designed to probe these core reasoning capabilities. Evaluation of state-of-the-art models on RiddleBench shows fundamental weaknesses. Even top proprietary models like Gemini 2.5 Pro, o3, and Claude 4 Sonnet achieve accuracy just above 60% (60.30%, 63.37%, and 63.16%). Analysis further reveals deep failures, including hallucination cascades (accepting flawed reasoning from other models) and poor self-correction due to a strong self-confirmation bias. Their reasoning is also fragile, with performance degrading significantly when constraints are reordered or irrelevant information is introduced. RiddleBench functions as a diagnostic tool for these issues and as a resource for guiding the development of more robust and reliable language models.

Low-resource languages face significant challenges due to the lack of sufficient linguistic data, resources, and tools for tasks such as supervised learning, annotation, and classification. This shortage hinders the development of accurate models and datasets, making it difficult to perform critical NLP tasks like sentiment analysis or hate speech detection. To bridge this gap, Large Language Models (LLMs) present an opportunity for potential annotators, capable of generating datasets and resources for these underrepresented languages. In this paper, we focus on Marathi, a low-resource language, and evaluate the performance of both closed-source and open-source LLMs as annotators. We assess models such as GPT-4o and Gemini 1.0 Pro, Gemma 2 (2B and 9B), and Llama 3.1 (8B) on classification tasks including sentiment analysis, news classification, and hate speech detection. Our findings reveal that while LLMs excel in annotation tasks for high-resource languages like English, they still fall short when applied to Marathi. Even advanced closed models like Gemini and GPT underperform in comparison to BERT-based baselines, highlighting the limitations of LLMs as annotators for low-resource languages.

Multi-modal large language models (MM-LLMs) have shown strong performance in medical image understanding and clinical reasoning. Recent medical agent systems extend them with tool use and multi-agent collaboration, enabling complex decision-making. However, these systems rely almost entirely on frontier models (e.g., GPT), whose API-based deployment incurs high cost, high latency, and privacy risks that conflict with on-premise clinical requirements. We present Meissa, a lightweight 4B-parameter medical MM-LLM that brings agentic capability offline. Instead of imitating static answers, Meissa learns both when to engage external interaction (strategy selection) and how to execute multi-step interaction (strategy execution) by distilling structured trajectories from frontier models. Specifically, we propose: (1) Unified trajectory modeling: trajectories (reasoning and action traces) are represented within a single state-action-observation formalism, allowing one model to generalize across heterogeneous medical environments. (2) Three-tier stratified supervision: the model's own errors trigger progressive escalation from direct reasoning to tool-augmented and multi-agent interaction, explicitly learning difficulty-aware strategy selection. (3) Prospective-retrospective supervision: pairing exploratory forward traces with hindsight-rationalized execution traces enables stable learning of effective interaction policies. Trained on 40K curated trajectories, Meissa matches or exceeds proprietary frontier agents in 10 of 16 evaluation settings across 13 medical benchmarks spanning radiology, pathology, and clinical reasoning. Using over 25x fewer parameters than typical frontier models like Gemini-3, Meissa operates fully offline with 22x lower end-to-end latency compared to API-based deployment. Data, models, and environments are released at https://github.com/Schuture/Meissa.

Rapid advances in multimodal models demand benchmarks that rigorously evaluate understanding and reasoning in safety-critical, dynamic real-world settings. We present AccidentBench, a large-scale benchmark that combines vehicle accident scenarios with Beyond domains, safety-critical settings in air and water that emphasize spatial and temporal reasoning (e.g., navigation, orientation, multi-vehicle motion). The benchmark contains approximately 2000 videos and over 19000 human-annotated question--answer pairs spanning multiple video lengths (short/medium/long) and difficulty levels (easy/medium/hard). Tasks systematically probe core capabilities: temporal, spatial, and intent understanding and reasoning. By unifying accident-centric traffic scenes with broader safety-critical scenarios in air and water, AccidentBench offers a comprehensive, physically grounded testbed for evaluating models under real-world variability. Evaluations of state-of-the-art models (e.g., Gemini-2.5 Pro and GPT-5) show that even the strongest models achieve only about 18% accuracy on the hardest tasks and longest videos, revealing substantial gaps in real-world temporal, spatial, and intent reasoning. AccidentBench is designed to expose these critical gaps and drive the development of multimodal models that are safer, more robust, and better aligned with real-world safety-critical challenges. The code and dataset are available at: https://github.com/SafeRL-Lab/AccidentBench

We introduce EgoPolice, a carefully curated dataset of real, egocentric police-civilian interactions, sourced from publicly available body-worn camera videos. We select police-civilian action labels that are critical for police behavioral research and annotate them at a second-by-second granularity. The videos feature rapid and irregular camera motion, dense human interactions, and rare high-stakes events, making the dataset a challenging benchmark for motion-robust and context-aware egocentric perception. We provide two different tasks, classification and multiple-choice question-answering, and benchmark both open-source and closed-source models. We find that even the best video models like Gemini 2.5 Pro still struggle to accurately predict high-risk actions such as "Weapon Out". Beyond serving as a benchmark, EgoPolice provides a foundation for developing models capable of identifying events of interest in large-scale body-worn camera video repositories, enabling more efficient downstream human review.

While End-to-End (E2E) Speech-Large Language Models (Speech-LLMs) are rapidly evolving, their evaluation methodologies remain limited to the era of simple transcription. Existing benchmarks suffer from three critical limitations: a pronounced bias towards high-resource languages, a focus on low-level recognition (ASR) rather than semantic reasoning, and a neglect of regional dialects. To bridge this gap, we introduce PolySpeech-100, a massive-scale benchmark designed to assess `native-level' speech comprehension across 110 linguistic variants. We employ a novel hybrid construction pipeline that augments gold-standard human recordings with instruction-driven synthetic speech, allowing us to cover 19 distinct Chinese dialects and over 80 low-resource languages. Extensive evaluation of 22 state-of-the-art models (including Gemini-3, GPT-Audio, and Qwen2.5-Omni) yields pivotal insights. First, we demonstrate that open-source E2E models outperform Cascade (ASR+LLM) systems on heavy dialects, proving that direct audio processing preserves critical paralinguistic cues and prosodic features (e.g., intonation, stress) that are often lost in standard transcription. Second, we reveal a significant performance gap: while commercial models maintain robustness, open-source models suffer catastrophic degradation on low-resource languages. Finally, counter-intuitively, we observe that under standard zero-shot settings, Chain-of-Thought prompting frequently degrades speech understanding performance for most evaluated models, revealing a potential modality alignment gap in current architectures. PolySpeech-100 establishes a rigorous standard for the next generation of inclusive, omni-capable Speech-LLMs. The data, demo, and code are publicly available at https://github.com/YoungSeng/PolySpeech-100.

The evolution of video generation toward complex, multi-shot narratives has exposed a critical deficit in current evaluation methods. Existing benchmarks remain anchored to single-shot paradigms, lacking the comprehensive story assets and cross-shot metrics required to assess long-form coherence and appeal. To bridge this gap, we introduce MSVBench, the first comprehensive benchmark featuring hierarchical scripts and reference images tailored for Multi-Shot Video generation. We propose a hybrid evaluation framework that synergizes the high-level semantic reasoning of Large Multimodal Models (LMMs) with the fine-grained perceptual rigor of ___domain-specific expert models. Evaluating 20 video generation methods across diverse paradigms, we find that current models--despite strong visual fidelity--primarily behave as visual interpolators rather than true world models. We further validate the reliability of our benchmark by demonstrating a state-of-the-art Spearman's rank correlation of 94.4% with human judgments. Finally, MSVBench extends beyond evaluation by providing a scalable supervisory signal. Fine-tuning a lightweight model on its pipeline-refined reasoning traces yields human-aligned performance comparable to commercial models like Gemini-2.5-Flash.

The mathematical capabilities of AI systems are complex and multifaceted. Most existing research has predominantly focused on the correctness of AI-generated solutions to mathematical problems. In this work, we argue that beyond producing correct answers, AI systems should also be capable of, or assist humans in, developing novel solutions to mathematical challenges. This study explores the creative potential of Large Language Models (LLMs) in mathematical reasoning, an aspect that has received limited attention in prior research. We introduce a novel framework and benchmark, CreativeMath, which encompasses problems ranging from middle school curricula to Olympic-level competitions, designed to assess LLMs' ability to propose innovative solutions after some known solutions have been provided. Our experiments demonstrate that, while LLMs perform well on standard mathematical tasks, their capacity for creative problem-solving varies considerably. Notably, the Gemini-1.5-Pro model outperformed other LLMs in generating novel solutions. This research opens a new frontier in evaluating AI creativity, shedding light on both the strengths and limitations of LLMs in fostering mathematical innovation, and setting the stage for future developments in AI-assisted mathematical discovery.

Multilingual translation stands as a challenging task for large language models (LLMs) to handle intricate language patterns and stilted translations that arise in automated translations. In this paper, we introduce Seed-X, a family of open-source LLMs comprising instruct and reasoning models, pushing the limits of translation capability with 7B parameter size. The base model is pre-trained on a diverse, high-quality dataset encompassing both monolingual and bilingual content across 28 languages, harnessing the full potential of multilingual data. The instruct model is then finetuned to translate by Chain-of-Thought (CoT) reasoning and further enhanced through reinforcement learning (RL) to achieve better generalization across diverse language pairs. Seed-X achieves performance comparable to leading closed-source models, including Gemini-2.5 and GPT-4o, across 28 languages, and significantly outperforms larger open-source models in both automatic metrics and human evaluations. We share the best practices through our optimization process, and make the parameter public available for advancing translation research and applications.

A prevalent assumption in LLM agent deployment holds that more structured harnesses universally improve reliability, and that higher-capability models need proportionally less structural guidance -- together implying a monotone inverse relationship between model capability tier and optimal harness complexity. We test this hypothesis through a controlled 432-run experiment crossing six models across four capability tiers with three harness conditions (light, balanced, strict) on HEAT-24, a 24-task synthetic benchmark with git-based workspace verification. Our results refute the monotone inverse relationship on two fronts. First, for the frontier chat model evaluated (Gemini 2.5 Flash), increased harness verbosity lowers VTSR by 29-38 percentage points -- a harness-complexity paradox. Second, for the frontier reasoning model evaluated (Qwen3.5-122B, extended thinking enabled), strict harness achieves the highest VTSR (91.7%) and the lowest latency, the opposite of the prediction. Within the constrained tier, a 2B model (Gemma4:e2B) matches strong-open-tier stability at 91.7% across all harnesses. Because each tier is represented by a single model in this study, these results should be interpreted as model-specific observations; harness sensitivity appears non-monotone across the models evaluated, and depends critically on model type (chat vs. reasoning). We introduce a six-label failure taxonomy showing that format_violation dominates capable-model failures while wrong_file dominates low-capability failures, and we derive practical tier-aware harness selection guidelines.

Following the recent achievement of gold-medal performance on the IMO by frontier LLMs, the community is searching for the next meaningful and challenging target for measuring LLM reasoning. Whereas olympiad-style problems measure step-by-step reasoning alone, research-level problems use such reasoning to advance the frontier of mathematical knowledge itself, emerging as a compelling alternative. Yet research-level math benchmarks remain scarce because such problems are difficult to source (e.g., Riemann Bench and FrontierMath-Tier 4 contain 25 and 50 problems, respectively). To support reliable evaluation of next-generation frontier models, we introduce Soohak, a 439-problem benchmark newly authored from scratch by 64 mathematicians. Soohak comprises two subsets. On the Challenge subset, frontier models including Gemini-3-Pro, GPT-5, and Claude-Opus-4.5 reach 30.4%, 26.4%, and 10.4% respectively, leaving substantial headroom, while leading open-weight models such as Qwen3-235B, GPT-OSS-120B, and Kimi-2.5 remain below 15%. Notably, beyond standard problem solving, Soohak introduces a refusal subset that probes a capability intrinsic to research mathematics: recognizing ill-posed problems and pausing rather than producing confident but unjustified answers. On this subset, no model exceeds 50%, identifying refusal as a new optimization target that current models do not directly address. To prevent contamination, the dataset will be publicly released in late 2026, with model evaluations available upon request in the interim.

Modern long-context large language models (LLMs) perform well on synthetic "needle-in-a-haystack" (NIAH) benchmarks, but such tests overlook how noisy contexts arise from biased retrieval and agentic workflows. We argue that haystack engineering is necessary to construct noisy long contexts that faithfully capture key real-world factors -- distraction from heterogeneous biased retrievers and cascading errors in agentic workflows -- to test models' long-context robustness. We instantiate it through HaystackCraft, a new NIAH benchmark built on the full English Wikipedia hyperlink network with multi-hop questions. HaystackCraft evaluates how heterogeneous retrieval strategies (e.g., sparse, dense, hybrid, and graph-based) affect distractor composition, haystack ordering, and downstream LLM performance. HaystackCraft further extends NIAH to dynamic, LLM-dependent settings that simulate agentic operations, where models refine queries, reflect on their past reasonings, and decide when to stop. Experiments with 15 long-context models show that (1) while stronger dense retrievers can introduce more challenging distractors, graph-based reranking simultaneously improves retrieval effectiveness and mitigates more harmful distractors; (2) in agentic tests, even advanced models like Gemini 2.5 Pro and GPT-5 suffer cascading failures from self-generated distractors or struggle to perform early stops. These results highlight persistent challenges in agentic long-context reasoning and establish HaystackCraft as a valuable testbed for future progress.

Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employing GPT-based agents have emerged as promising solutions. However, fine-tuning LVLMs would require extensive high-quality data and substantial GPU resources, while GPT-based agents would rely on proprietary models (e.g., GPT-4o). In this paper, we propose Video Retrieval-Augmented Generation (Video-RAG), a training-free and cost-effective pipeline that employs visually-aligned auxiliary texts to help facilitate cross-modality alignment while providing additional information beyond the visual content. Specifically, we leverage open-source external tools to extract visually-aligned information from pure video data (e.g., audio, optical character, and object detection), and incorporate the extracted information into an existing LVLM as auxiliary texts, alongside video frames and queries, in a plug-and-play manner. Our Video-RAG offers several key advantages: (i) lightweight with low computing overhead due to single-turn retrieval; (ii) easy implementation and compatibility with any LVLM; and (iii) significant, consistent performance gains across long video understanding benchmarks, including Video-MME, MLVU, and LongVideoBench. Notably, our model demonstrates superior performance over proprietary models like Gemini-1.5-Pro and GPT-4o when utilized with a 72B model.

This paper introduces Werewolf Arena, a novel framework for evaluating large language models (LLMs) through the lens of the classic social deduction game, Werewolf. In Werewolf Arena, LLMs compete against each other, navigating the game's complex dynamics of deception, deduction, and persuasion. The framework introduces a dynamic turn-taking system based on bidding, mirroring real-world discussions where individuals strategically choose when to speak. We demonstrate the framework's utility through an arena-style tournament featuring Gemini and GPT models. Our results reveal distinct strengths and weaknesses in the models' strategic reasoning and communication. These findings highlight Werewolf Arena's potential as a challenging and scalable LLM benchmark.

When multiple large language models interact in a shared conversation, do they develop differentiated social roles or converge toward uniform behavior? We present a controlled experimental platform that orchestrates simultaneous multi-agent discussions among 7 heterogeneous LLMs on a unified inference backend, systematically varying group composition, naming conventions, and prompt structure across 12 experimental series (208 runs, 13,786 coded messages). Each message is independently coded on six behavioral flags by two LLM judges from distinct model families (Gemini 3.1 Pro and Claude Sonnet 4.6), achieving mean Cohen's kappa = 0.78 with conservative intersection-based adjudication. Human validation on 609 randomly stratified messages confirmed coding reliability (mean kappa = 0.73 vs. Gemini). We find that (1) heterogeneous groups exhibit significantly richer behavioral differentiation than homogeneous groups (cosine similarity 0.56 vs. 0.85; p < 10^-5, r = 0.70); (2) groups spontaneously exhibit compensatory response patterns when an agent crashes; (3) revealing real model names significantly increases behavioral convergence (cosine 0.56 to 0.77, p = 0.001); and (4) removing all prompt scaffolding converges profiles to homogeneous-level similarity (p < 0.001). Critically, these behaviors are absent when agents operate in isolation, confirming that behavioral diversity is a structured, reproducible phenomenon driven by the interaction of architectural heterogeneity, group context, and prompt-level scaffolding.

The advancement of large language models (LLMs) has allowed them to be proficient in various tasks, including content generation. However, their unregulated usage can lead to malicious activities such as plagiarism and generating and spreading fake news, especially for low-resource languages. Most existing machine-generated text detectors are trained on high-resource languages like English, French, etc. In this study, we developed the first large-scale detector that can distinguish between human- and machine-generated content in Hausa. We scrapped seven Hausa-language media outlets for the human-generated text and the Gemini-2.0 flash model to automatically generate the corresponding Hausa-language articles based on the human-generated article headlines. We fine-tuned four pre-trained Afri-centric models (AfriTeVa, AfriBERTa, AfroXLMR, and AfroXLMR-76L) on the resulting dataset and assessed their performance using accuracy and F1-score metrics. AfroXLMR achieved the highest performance with an accuracy of 99.23% and an F1 score of 99.21%, demonstrating its effectiveness for Hausa text detection. Our dataset is made publicly available to enable further research.

Medical audio data is difficult to collect due to privacy regulations and high annotation costs arising from ___domain expertise. Thus, existing benchmarks tend to underrepresent complex medical audio scenarios. To address this challenge, we present MedMosaic, a medical audio question-answering dataset designed to benchmark language and audio reasoning models under realistic clinical constraints. MedMosaic features a diverse range of medical audio types, including condition-related physiological sounds, carefully constructed synthetic voices to mimic speech with artifacts as well as real short and long length clinical conversations to model varying context lengths. The dataset also features a total of 46,701 question-answer pairs, spanning categories such as multiple-choice, sequential multi-turn, and open-ended question-answers, enabling systematic evaluation of multi-hop reasoning and answer generation capabilities. Benchmarking 13 audio and multimodal reasoning models reveals that reasoning remains challenging for all evaluated systems, with substantial performance variation across question types. In particular, even state-of-the-art model like Gemini-2.5-pro can only achieve 68.1% accuracy approximately. These findings underscore persistent limitations in medical reasoning and highlight the need for more robust, ___domain-specific multimodal reasoning models. A sample of benchmark data is available here: https://shorturl.at/Lyp33

This is the fourth in a series of short reports that help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. Here, we ask whether assigning personas to models improves performance on difficult objective multiple-choice questions. We study both ___domain-specific expert personas and low-knowledge personas, evaluating six models on GPQA Diamond (Rein et al. 2024) and MMLU-Pro (Wang et al. 2024), graduate-level questions spanning science, engineering, and law. We tested three approaches: -In-Domain Experts: Assigning the model an expert persona ("you are a physics expert") matched to the problem type (physics problems) had no significant impact on performance (with the exception of the Gemini 2.0 Flash model). -Off-Domain Experts (Domain-Mismatched): Assigning the model an expert persona ("you are a physics expert") not matched to the problem type (law problems) resulted in marginal differences. -Low-Knowledge Personas: We assigned the model negative capability personas (layperson, young child, toddler), which were generally harmful to benchmark accuracy. Across both benchmarks, persona prompts generally did not improve accuracy relative to a no-persona baseline. Expert personas showed no consistent benefit across models, with few exceptions. Domain-mismatched expert personas sometimes degraded performance. Low-knowledge personas often reduced accuracy. These results are about the accuracy of answers only; personas may serve other purposes (such as altering the tone of outputs), beyond improving factual performance.

Large Language Models have demonstrated remarkable capabilities across diverse domains, yet significant challenges persist when deploying them as AI agents for real-world long-horizon tasks. Existing LLM agents suffer from a critical limitation: they are test-time static and cannot learn from experience, lacking the ability to accumulate knowledge and continuously improve on the job. To address this challenge, we propose MUSE, a novel agent framework that introduces an experience-driven, self-evolving system centered around a hierarchical Memory Module. MUSE organizes diverse levels of experience and leverages them to plan and execute long-horizon tasks across multiple applications. After each sub-task execution, the agent autonomously reflects on its trajectory, converting the raw trajectory into structured experience and integrating it back into the Memory Module. This mechanism enables the agent to evolve beyond its static pretrained parameters, fostering continuous learning and self-evolution. We evaluate MUSE on the long-horizon productivity benchmark TAC. It achieves new SOTA performance by a significant margin using only a lightweight Gemini-2.5 Flash model. Sufficient Experiments demonstrate that as the agent autonomously accumulates experience, it exhibits increasingly superior task completion capabilities, as well as robust continuous learning and self-evolution capabilities. Moreover, the accumulated experience from MUSE exhibits strong generalization properties, enabling zero-shot improvement on new tasks. MUSE establishes a new paradigm for AI agents capable of real-world productivity task automation.

A key challenge in evaluating VLMs is testing models' ability to analyze visual content independently from their textual priors. Recent benchmarks such as BLINK probe visual perception through visual prompting, where questions about visual content are paired with coordinates to which the question refers, with the coordinates explicitly marked in the image itself. While these benchmarks are an important part of VLM evaluation, we find that existing models are surprisingly fragile to seemingly irrelevant details of visual prompting: simply changing a visual marker from red to blue can completely change rankings among models on a leaderboard. By evaluating nine commonly-used open- and closed-source VLMs on two visually prompted tasks, we demonstrate how details in benchmark setup, including visual marker design and dataset size, have a significant influence on model performance and leaderboard rankings. These effects can even be exploited to lift weaker models above stronger ones; for instance, slightly increasing the size of the visual marker results in open-source InternVL3-8B ranking alongside or better than much larger proprietary models like Gemini 2.5 Pro. We further show that low-level inference choices that are often ignored in benchmarking, such as JPEG compression levels in API calls, can also cause model lineup changes. These details have substantially larger impacts on visually prompted benchmarks than on conventional semantic VLM evaluations. To mitigate this instability, we curate existing datasets to create VPBench, a larger visually prompted benchmark with 16 visual marker variants. We open-source VPBench and our analysis framework at: https://lisadunlap.github.io/vpbench/.

Document parsing aims to transform unstructured PDF images into semi-structured data, facilitating the digitization and utilization of information in diverse domains. While vision language models (VLMs) have significantly advanced this task, achieving reliable, high-quality parsing in real-world scenarios remains challenging. Common practice often selects the top-performing model on standard benchmarks. However, these benchmarks may carry dataset-specific biases, leading to inconsistent model rankings and limited correlation with real-world performance. Moreover, benchmark metrics typically provide only overall scores, which can obscure distinct error patterns in output. This raises a key challenge: how can we reliably and comprehensively assess document parsing quality in the wild? We address this problem with DOCR-Inspector, which formalizes document parsing assessment as fine-grained error detection and analysis. Leveraging VLM-as-a-Judge, DOCR-Inspector analyzes a document image and its parsed output, identifies all errors, assigns them to one of 28 predefined types, and produces a comprehensive quality assessment. To enable this capability, we construct DOCRcase-200K for training and propose the Chain-of-Checklist reasoning paradigm to enable the hierarchical structure of parsing quality assessment. For empirical validation, we introduce DOCRcaseBench, a set of 882 real-world document parsing cases with manual annotations. On this benchmark, DOCR-Inspector-7B outperforms commercial models like Gemini 2.5 Pro, as well as leading open-source models. Further experiments demonstrate that its quality assessments provide valuable guidance for parsing results refinement, making DOCR-Inspector both a practical evaluator and a driver for advancing document parsing systems at scale. Model and code are released at: https://github.com/ZZZZZQT/DOCR-Inspector.

Effective de-escalation is critical for law enforcement safety and community trust, yet traditional training methods lack scalability and realism. While Large Language Models (LLMs) enable dynamic, open-ended simulations, their substantial computational footprint renders them impractical for deployment on the lightweight, portable hardware required for immersive field training. Small Language Models (SLMs) offer a viable real-time alternative but suffer from a critical scarcity of high-quality, ___domain-specific training data. To bridge this gap, we present DeEscalWild, a novel benchmark dataset curated from a multi-stage pipeline of in-the-wild police-civilian interactions extracted from publicly available video repositories. Starting with 5,000 raw inputs, we employed a rigorous hybrid filtering process combining human-in-the-loop verification with LLM-as-a-Judge evaluation to distill 1,500 high-fidelity scenarios. The resulting corpus comprises 285,887 dialogue turns, totaling approximately 4.7 million tokens. Extensive experiments demonstrate that SLMs fine-tuned on this data significantly outperform their base counterparts across ROUGE-L, BLEU-4, METEOR, BERTScore, Realism Score, and human evaluation metrics. Notably, our fine-tuned Qwen 2.5 (3B-Instruct) surpasses the general-purpose Gemini 2.5 Flash model when evaluated under equivalent conditions, demonstrating that ___domain-optimized SLMs can achieve superior performance with a fraction of the computational cost. This work establishes the foundational infrastructure for accessible, low-latency, and privacy-preserving officer training systems at the edge. We publicly release our code(https://github.com/Hasebul/DeEscalWild-Benchmark-Framework) and dataset(https://doi.org/10.7910/DVN/CWMCZI).

Despite progress on general tasks, VLMs struggle with challenges demanding both detailed visual grounding and deliberate knowledge-based reasoning, a synergy not captured by existing benchmarks that evaluate these skills separately. To close this gap, we introduce Pix2Fact, a new visual question-answering benchmark designed to evaluate expert-level perception and knowledge-intensive multi-hop reasoning. Pix2Fact contains 1,000 high-resolution (4K+) images spanning 8 daily-life scenarios and situations, with questions and answers meticulously crafted by annotators holding PhDs from top global universities working in partnership with a professional data annotation firm. Each question requires detailed visual grounding, multi-hop reasoning, and the integration of external knowledge to answer. Our evaluation of 9 state-of-the-art VLMs, including proprietary models like Gemini-3-Pro and GPT-5, reveals the substantial challenge posed by Pix2Fact: the most advanced model achieves only 24.0% average accuracy, in stark contrast to human performance of 56%. This significant gap underscores the limitations of current models in replicating human-level visual comprehension. We believe Pix2Fact will serve as a critical benchmark to drive the development of next-generation multimodal agents that combine fine-grained perception with robust, knowledge-based reasoning.