Apple ML Research: On-Policy Distillation's Benefits and Pitfalls

Jul 10, 2026

Apple Machine Learning Research published a study examining on-policy distillation for training reasoning models, focusing on when per-token supervision is beneficial or detrimental. The research introduces a training-free method to analyze token-level dynamics, addressing questions about optimal teacher selection and supervisory context in self-distillation.

Why it matters: This research offers a framework to better understand the token-level effects of distillation, potentially reducing the need for costly trial-and-error in training reasoning models.

Full story at: Apple Machine Learning Research ↗