# Teaching Small AI Models to Learn From Their Own Mistakes

AlphaSignal, 2026-10-24. [Read the original](https://alphasignal.ai/news/teaching-small-ai-models-to-learn-from-their-own-mistakes).

A survey by Mingyang Song and Mao Zheng maps the scattered literature on on-policy distillation, where a small model learns from its own mistakes.