# One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation > Source: > Published: 2026-09-08 07:30:10+00:00 On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of imitation learning with the on-policy sampling of reinforcement learning. But it requires a second, larger model to act as teacher. On-Policy Self-Di