Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper about 19 hours ago

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Paper • 2605.23904 • Published 4 days ago • 153

upvoted 2 papers 5 days ago

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

Paper • 2605.21468 • Published 6 days ago • 47

The Unlearnability Phenomenon in RLVR for Language Models

Paper • 2605.16787 • Published 10 days ago • 5

upvoted a paper 6 days ago

Process Rewards with Learned Reliability

Paper • 2605.15529 • Published 11 days ago • 52

upvoted a paper 14 days ago

G-Zero: Self-Play for Open-Ended Generation from Zero Data

Paper • 2605.09959 • Published 15 days ago • 17

upvoted a paper 15 days ago

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

Paper • 2605.08083 • Published 18 days ago • 68

upvoted a paper 16 days ago

SkillOS: Learning Skill Curation for Self-Evolving Agents

Paper • 2605.06614 • Published 19 days ago • 45

upvoted a paper 17 days ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 23 days ago • 114

upvoted a paper 18 days ago

Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration

Paper • 2605.05566 • Published 19 days ago • 37

upvoted a paper 26 days ago

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published 28 days ago • 273

upvoted 2 papers about 1 month ago

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

Paper • 2604.13602 • Published Apr 15 • 32

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published Apr 15 • 162

upvoted 2 papers about 2 months ago

Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills

Paper • 2604.05333 • Published Apr 7 • 22

MARS: Enabling Autoregressive Models Multi-Token Generation

Paper • 2604.07023 • Published Apr 8 • 38

upvoted 2 papers 2 months ago

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published Mar 17 • 140

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published Mar 10 • 43

upvoted 4 papers 3 months ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published Mar 10 • 53

Surgical Post-Training: Cutting Errors, Keeping Knowledge

Paper • 2603.01683 • Published Mar 2 • 12

SkillOrchestra: Learning to Route Agents via Skill Transfer

Paper • 2602.19672 • Published Feb 23 • 58

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 150