# SeOPD: Self-Evolving LLMs via Online Policy Distillation from Self-Generated Chain-of-Thought

arXiv: https://arxiv.org/abs/2609.33181 · HTML: https://mlsanity.com/paper/2609.33181/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)
- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)
- Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/)

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [On-Policy Context Distillation for Language Models](https://mlsanity.com/paper/2602.12275/) (2026)
- [A Survey of On-Policy Distillation for Large Language Models](https://mlsanity.com/paper/2604.00626/) (2026)
- [Privileged Information Distillation for Language Models](https://mlsanity.com/paper/2602.04942/) (2026)
- [Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents](https://mlsanity.com/paper/2604.10674/) (2026)
- [HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation](https://mlsanity.com/paper/2603.23871/) (2026)
- [SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models](https://mlsanity.com/paper/2406.09098/) (2024)
- [On-Policy Self-Distillation without Any Supervision](https://mlsanity.com/paper/2608.06296/) (2026)
- [When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale](https://mlsanity.com/paper/2309.04564/) (2023)
- [On-Policy Distillation with Best-of-N Teacher Rollout Selection](https://mlsanity.com/paper/2605.09725/) (2026)
- [Skill-Conditioned Gated Self-Distillation for LLM Reasoning](https://mlsanity.com/paper/2605.28791/) (2026)
- [Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism](https://mlsanity.com/paper/2510.13170/) (2025)

## Abstract (arXiv)

Recent advances in online policy self-distillation (OPSD) have demonstrated that large language models (LLMs) can improve their capabilities by leveraging external privileged information (PI), such as manual annotations or feedback from external environments. However, obtaining accurate annotations and constructing sophisticated environments often require substantial human effort and computation, limiting the scalability of OPSD. While a few recent studies have explored self-improvement without external PI, the resulting gains remain limited. In this work, we explore whether LLMs can achieve comparable self-improvement without external PI. Our key observation is that a single LLM can support multiple reasoning modes, such as deep-thinking and non-thinking modes, with deep thinking generating additional information during reasoning. Based on this observation, we propose Self-Evolving Online Policy Distillation (SeOPD), which enables LLMs to distill and internalize information generated by their own chain of thought (CoT). Specifically, it (1) generates CoT with the deep-thinking mode, (2) produces responses with the non-thinking mode, and (3) uses the generated CoT as PI to provide token-level supervision for the non-thinking response, allowing new information inferred during reasoning to guide the non-thinking mode and be internalized into the shared model parameters, thereby improving both non-thinking and deep-thinking capabilities. Extensive experiments across LLMs and tasks demonstrate the effectiveness of SeOPD.