Lei Wang

demolei's activity

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

upvoted 2 papers 3 days ago

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

Paper • 2607.12625 • Published 6 days ago • 56

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

Paper • 2607.14777 • Published 5 days ago • 93

upvoted 2 papers 4 days ago

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

Paper • 2607.08964 • Published 12 days ago • 74

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

Paper • 2607.13285 • Published 7 days ago • 203

upvoted a paper 10 days ago

Gemma 4 Technical Report

Paper • 2607.02770 • Published 19 days ago • 68

upvoted 3 papers 12 days ago

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

Paper • 2607.05804 • Published 14 days ago • 18

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

Paper • 2607.05147 • Published 15 days ago • 36

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published 18 days ago • 79

upvoted 2 papers 18 days ago

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

Paper • 2606.28733 • Published 24 days ago • 148

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published 25 days ago • 111

upvoted a paper 20 days ago

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

Paper • 2606.28480 • Published 25 days ago • 48

upvoted 5 papers 24 days ago

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

Paper • 2606.26027 • Published 27 days ago • 18

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

Paper • 2606.24551 • Published 29 days ago • 28

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Paper • 2606.26300 • Published 27 days ago • 51

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Paper • 2606.26790 • Published 26 days ago • 56

DanceOPD: On-Policy Generative Field Distillation

Paper • 2606.27377 • Published 26 days ago • 81

upvoted 2 papers 26 days ago

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 384

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

Paper • 2606.22388 • Published 30 days ago • 95

upvoted 2 papers 27 days ago

OpenThoughts-Agent: Data Recipes for Agentic Models

Paper • 2606.24855 • Published 28 days ago • 47

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published 28 days ago • 149