# On-Policy Distillation, Simply Explained

DevFeed: [On-Policy Distillation, Simply Explained](<https://devfeed.tech/articles/on-policy-distillation-simply-explained-18280.md>)

Original publisher: [Read original article](<https://www.intoai.pub/p/on-policy-distillation>)

Author: Dr. Ashish Bamania

Published: 2026-09-09T19:22:38Z

Content type: tutorial

Language: en

Sources: [Into AI](<https://devfeed.tech/sources/into-ai.md>)

Topics: [LLM Techniques](<https://devfeed.tech/topics/llm-techniques.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [post-training](<https://devfeed.tech/topics/post-training.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>)

Tags: [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [llms](<https://devfeed.tech/tags/llms.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [training](<https://devfeed.tech/tags/training.md>)

## AI overview

This tutorial explains on-policy distillation (OPD), a post-training method for large language models. A student model generates its own responses, which a stronger teacher scores token by token; the student is trained to reduce the reverse KL divergence between their next-token distributions. The article distinguishes OPD from reinforcement learning, conventional knowledge distillation, and supervised fine-tuning.

## Source excerpt

On-Policy Distillation (OPD) has become a popular algorithm for post-training LLMs, and almost all recent open-weight LLMs (Qwen3, GLM-5.3, and Nemotron-Cascade 2) have used it to achieve amazing performance.