Lei Wang

demolei's activity

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

upvoted a paper about 15 hours ago

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Paper • 2607.24223 • Published 3 days ago • 81

upvoted a paper about 19 hours ago

From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search

Paper • 2607.24280 • Published 3 days ago • 74

upvoted 2 papers 1 day ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 3 days ago • 339

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents

Paper • 2607.22798 • Published 6 days ago • 55

upvoted 4 papers 13 days ago

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

Paper • 2607.12625 • Published 15 days ago • 80

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

Paper • 2607.14777 • Published 14 days ago • 103

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

Paper • 2607.08964 • Published 21 days ago • 76

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

Paper • 2607.13285 • Published 16 days ago • 227

upvoted a paper 20 days ago

Gemma 4 Technical Report

Paper • 2607.02770 • Published 28 days ago • 75

upvoted 3 papers 21 days ago

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

Paper • 2607.05804 • Published 23 days ago • 19

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

Paper • 2607.05147 • Published 24 days ago • 39

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published 27 days ago • 82

upvoted 2 papers 28 days ago

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

Paper • 2606.28733 • Published Jun 27 • 150

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published Jun 26 • 113

upvoted a paper 29 days ago

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

Paper • 2606.28480 • Published Jun 26 • 48

upvoted 5 papers about 1 month ago

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

Paper • 2606.26027 • Published Jun 24 • 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 Jun 24 • 51

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Paper • 2606.26790 • Published Jun 25 • 57

DanceOPD: On-Policy Generative Field Distillation

Paper • 2606.27377 • Published Jun 25 • 81