Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning

ArXi:2605.13255v1 Announce Type: new On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provides dense token-level supervision. Existing objectives typically weight the teacher's token-level signal uniformly across a chain-of-thought sequence, despite substantial variation in the entropy of the teacher's predictive distribution.