SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Paper • 2608.03573 • Published about 1 month ago • 60
On-Policy Self-Distillation without Any Supervision Paper • 2608.06296 • Published 27 days ago • 218
Beacon: Knowing When and How to Perform Agentic Visual Reasoning Paper • 2607.28595 • Published Jul 30 • 55