Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents Paper • 2605.30723 • Published 5 days ago • 10
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 7 days ago • 417
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 21 days ago • 270
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Paper • 2605.06130 • Published 27 days ago • 111
GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction Paper • 2604.23941 • Published Apr 27 • 6