Lei Wang

demolei's activity

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

upvoted 2 papers 4 days ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published 6 days ago • 90

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Paper • 2607.28609 • Published 13 days ago • 68

upvoted 6 papers 5 days ago

Dr. Zero: Self-Evolving Search Agents without Training Data

Paper • 2601.07055 • Published Jan 11 • 23

Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Paper • 2601.18778 • Published Jan 26 • 44

Recursive Harness Self-Improvement

Paper • 2607.15524 • Published 26 days ago • 26

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

Paper • 2606.08671 • Published Jun 23 • 47

EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?

Paper • 2607.09711 • Published Jun 23 • 1

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Paper • 2607.28568 • Published 13 days ago • 182

upvoted 4 papers 7 days ago

SAF-OPD: Stable Advantage Fusion for On-Policy Distillation

Paper • 2607.29209 • Published 12 days ago • 34

Progressive Agent Skill Generation via Reinforcement Learning

Paper • 2608.01678 • Published 9 days ago • 58

PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

Paper • 2608.04003 • Published 7 days ago • 33

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Paper • 2608.01964 • Published 9 days ago • 166

upvoted a paper 9 days ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published 17 days ago • 105

upvoted a paper 12 days ago

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Paper • 2607.28227 • Published 13 days ago • 302

upvoted 2 papers 14 days ago

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

Paper • 2607.24223 • Published 16 days ago • 95

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

Paper • 2607.24280 • Published 16 days ago • 83

upvoted 2 papers 15 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 16 days ago • 489

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

Paper • 2607.22798 • Published 19 days ago • 62

upvoted 2 papers 26 days ago

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

Paper • 2607.12625 • Published 28 days ago • 81

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

Paper • 2607.14777 • Published 27 days ago • 106