Lei Wang

demolei's activity

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

upvoted 4 papers 6 days ago

KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill

Paper • 2607.12625 • Published 8 days ago • 59

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published 7 days ago • 96

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published 14 days ago • 74

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published 9 days ago • 213

upvoted a paper 13 days ago

Gemma 4 Technical Report

Paper • 2607.02770 • Published 21 days ago • 69

upvoted 3 papers 15 days ago

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

Paper • 2607.05804 • Published 16 days ago • 18

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

Paper • 2607.05147 • Published 17 days ago • 37

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published 20 days ago • 80

upvoted 2 papers 21 days ago

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

Paper • 2606.28733 • Published 26 days ago • 148

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published 27 days ago • 111

upvoted a paper 23 days ago

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

Paper • 2606.28480 • Published 27 days ago • 48

upvoted 5 papers 27 days ago

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Paper • 2606.26027 • Published 29 days ago • 18

GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents

Paper • 2606.24551 • Published Jun 22 • 28

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Paper • 2606.26300 • Published 29 days ago • 51

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Paper • 2606.26790 • Published 28 days ago • 56

DanceOPD: On-Policy Generative Field Distillation

Paper • 2606.27377 • Published 28 days ago • 81

upvoted a paper 28 days ago

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 384

upvoted 3 papers 29 days ago

PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

Paper • 2606.22388 • Published Jun 21 • 95

OpenThoughts-Agent: Data Recipes for Agentic Models

Paper • 2606.24855 • Published about 1 month ago • 47

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published about 1 month ago • 151