COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation Paper • 2605.31264 • Published 13 days ago • 111
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 15 days ago • 423
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards Paper • 2605.21467 • Published 22 days ago • 204
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published 30 days ago • 195
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution Paper • 2605.09942 • Published about 1 month ago • 15
MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU Paper • 2604.05091 • Published Apr 6 • 47