Yuxin Chai

YXYXChAI's activity

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

upvoted 6 papers about 4 hours ago

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

Paper • 2610.09832 • Published 6 days ago • 13

CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use

Paper • 2610.09127 • Published 7 days ago • 21

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 6 days ago • 39

ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation

Paper • 2609.39306 • Published 13 days ago • 40

DecepEval: A Benchmark for Evaluating Deception in LLM Agents

Paper • 2610.07967 • Published 7 days ago • 83

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

Paper • 2610.10409 • Published 6 days ago • 35

upvoted a paper about 24 hours ago

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

Paper • 2610.01892 • Published 12 days ago • 37

upvoted 5 papers 2 days ago

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

Paper • 2609.39378 • Published 13 days ago • 74

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

Paper • 2610.07557 • Published 7 days ago • 71

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

Paper • 2609.32520 • Published 17 days ago • 25

AutoDataBench: A Data-centric Testbed for Accelerating Auto Research

Paper • 2609.40097 • Published 13 days ago • 50

EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation

Paper • 2610.07969 • Published 7 days ago • 22

upvoted 4 papers 3 days ago

Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training

Paper • 2610.07510 • Published 8 days ago • 14

EVISKILL: Grounding Skill Evolution in Replayable Evidence

Paper • 2610.05030 • Published 9 days ago • 53

DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks

Paper • 2610.08048 • Published 7 days ago • 17

TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning

Paper • 2610.07043 • Published 8 days ago • 44

upvoted 3 papers 4 days ago

LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures

Paper • 2610.04292 • Published 10 days ago • 38

Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym

Paper • 2609.37267 • Published 14 days ago • 40

Empirical Variational Autoencoder

Paper • 2610.06545 • Published 8 days ago • 11

upvoted a paper 5 days ago

Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems

Paper • 2609.39050 • Published 13 days ago • 18