siyeng feng

siyengfeng's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 4 papers 7 days ago

AutoMem: Automated Learning of Memory as a Cognitive Skill

Paper • 2607.01224 • Published 10 days ago • 19

SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

Paper • 2607.01874 • Published 9 days ago • 18

AgenticDataBench: A Comprehensive Benchmark for Data Agents

Paper • 2607.01647 • Published 9 days ago • 35

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published 12 days ago • 47

liked a Space 8 days ago

Running

52

Don't Train the Model, Evolve the Harness

🌿

52

Evolving an agent's harness, not its model, on Harvey's LAB

liked a dataset 8 days ago

nvidia/SWE-Zero-openhands-trajectories

Viewer • Updated May 5 • 318k • 1.89k • 17

upvoted a collection 8 days ago

swe-zero-to-swe-hero

Collection

Datasets and Models for SWE-ZERO to SWE-HERO paper (https://arxiv.org/abs/2604.01496) • 6 items • Updated 10 days ago • 6

upvoted 7 papers 9 days ago

The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems

Paper • 2605.21997 • Published May 21 • 2

MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training

Paper • 2606.30406 • Published 12 days ago • 15

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

Paper • 2606.08671 • Published 18 days ago • 43

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Paper • 2606.29082 • Published 14 days ago • 41

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published 12 days ago • 103

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published 15 days ago • 109

Orca: The World is in Your Mind

Paper • 2606.30534 • Published 12 days ago • 310

upvoted 5 papers 10 days ago

ReFreeKV: Towards Threshold-Free KV Cache Compression

Paper • 2502.16886 • Published 15 days ago • 48

AsyncOPD: How Stale Can On-Policy Distillation Be?

Paper • 2606.24143 • Published 18 days ago • 30

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

Paper • 2606.28480 • Published 15 days ago • 47

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Paper • 2606.30616 • Published 12 days ago • 98

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Paper • 2606.28733 • Published 14 days ago • 146

upvoted a paper 14 days ago

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

Paper • 2606.16613 • Published 26 days ago • 9