Yuxin Chai

YXYXChAI's activity

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

upvoted a paper about 13 hours ago

Harness^2: Recursive Agent Harnessing for an Open World

Paper • 2610.14224 • Published 8 days ago • 103

upvoted a paper 1 day ago

Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training

Paper • 2610.12933 • Published 8 days ago • 12

upvoted 2 papers 2 days ago

Stateless Language Agents: Scaling Long-Horizon Automated Research

Paper • 2610.07625 • Published 11 days ago • 29

DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

Paper • 2610.12572 • Published 9 days ago • 317

upvoted 5 papers 3 days ago

From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

Paper • 2610.06100 • Published 12 days ago • 142

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

Paper • 2610.11794 • Published 9 days ago • 45

Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?

Paper • 2610.08215 • Published 9 days ago • 156

A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization

Paper • 2610.12183 • Published 9 days ago • 14

OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning

Paper • 2610.12458 • Published 9 days ago • 17

upvoted 7 papers 5 days ago

SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles

Paper • 2610.09832 • Published 10 days ago • 14

CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use

Paper • 2610.09127 • Published 11 days ago • 22

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 10 days ago • 40

ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation

Paper • 2609.39306 • Published 17 days ago • 42

DecepEval: A Benchmark for Evaluating Deception in LLM Agents

Paper • 2610.07967 • Published 11 days ago • 85

RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments

Paper • 2610.10409 • Published 10 days ago • 40

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

Paper • 2610.01892 • Published 16 days ago • 38

upvoted 4 papers 6 days ago

EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos

Paper • 2609.39378 • Published 17 days ago • 74

CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?

Paper • 2610.07557 • Published 11 days ago • 76

When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents

Paper • 2609.32520 • Published 21 days ago • 25

AutoDataBench: A Data-centric Testbed for Accelerating Auto Research

Paper • 2609.40097 • Published 17 days ago • 50