Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper 2 days ago

Self-Evolving Agent Harness

Paper • 2610.18813 • Published 6 days ago • 203

upvoted a paper 3 days ago

Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine

Paper • 2610.22192 • Published 4 days ago • 26

upvoted a paper 5 days ago

Harness^2: Recursive Agent Harnessing for an Open World

Paper • 2610.14224 • Published 10 days ago • 114

upvoted a paper 7 days ago

ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents

Paper • 2610.13395 • Published 10 days ago • 54

upvoted a paper 10 days ago

nanoMuse: An Open-Source Personal Agent for Every Device You Own

Paper • 2610.08699 • Published 13 days ago • 116

upvoted a paper 11 days ago

Questioning the Questions: Sustaining Self-Evolution in Reasoning Models

Paper • 2610.04299 • Published 16 days ago • 85

upvoted a paper 12 days ago

SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting

Paper • 2610.04109 • Published 17 days ago • 35

upvoted a paper 14 days ago

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

Paper • 2610.02826 • Published 17 days ago • 106

upvoted a paper 17 days ago

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published 19 days ago • 277

upvoted a paper 18 days ago

On the Off-Policy Teacher in On-Policy Distillation

Paper • 2609.38360 • Published 20 days ago • 24

upvoted 3 papers 19 days ago

TabFM: A Zero-Shot Foundation Model for Tabular Data

Paper • 2609.37959 • Published 20 days ago • 21

Adversarial Training for Pixel Diffusion

Paper • 2609.38170 • Published 20 days ago • 22

TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs

Paper • 2609.33589 • Published 22 days ago • 9

upvoted a paper 21 days ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 24 days ago • 144

upvoted 2 papers 27 days ago

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 28 days ago • 230

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

Paper • 2609.22086 • Published about 1 month ago • 35

upvoted 4 papers about 1 month ago

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published Sep 14 • 333

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Paper • 2609.11115 • Published Sep 10 • 220

Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs

Paper • 2609.11499 • Published Sep 10 • 33

Programmable World Model

Paper • 2609.10540 • Published Sep 9 • 94