On-Policy Distillation: Frontier Reasoning on Small Models

1Key Takeaways

• Originally published on AI Tech Connect .
• What you need to know The idea in one line.
• The small "student" model generates its own answers, and a stronger "teacher" grades those answers token by token — so the student learns from its own mistakes, not from a transcript it can only mimic.
• Copying a teacher's perfect outputs (off-policy) makes small errors compound over long reasoning chains.