Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
Paper • 2603.25562 • Published • 19
RL
RL
-
-
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 111 -
DRAGON: Distributional Rewards Optimize Diffusion Generative Models
Paper • 2504.15217 • Published • 11 -
Diffusion Policy Policy Optimization
Paper • 2409.00588 • Published • 20 -
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Paper • 2510.25992 • Published • 48 -
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Paper • 2605.11609 • Published • 195 -
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Paper • 2606.03979 • Published • 25 -
Self-Distilled Policy Gradient
Paper • 2606.04036 • Published • 22