Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 6 days ago • 304
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published 5 days ago • 265
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published 11 days ago • 350
Memory-Augmented Vision-Language Agents for Persistent and Semantically Consistent Object Captioning Paper • 2603.24257 • Published 15 days ago • 6
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Paper • 2604.03922 • Published 9 days ago • 52