# SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning

arXiv: https://arxiv.org/abs/2608.14277 · HTML: https://mlsanity.com/paper/2608.14277/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)
- 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, 22 of 22)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe](https://mlsanity.com/paper/2604.13016/) (2026)
- [Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation](https://mlsanity.com/paper/2602.12125/) (2026)
- [Entropy-Aware On-Policy Distillation of Language Models](https://mlsanity.com/paper/2603.07079/) (2026)
- [Towards Robust Mathematical Reasoning](https://mlsanity.com/paper/2511.01846/) (2025)
- [FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks](https://mlsanity.com/paper/2601.21165/) (2026)
- [AMO-Bench: Large Language Models Still Struggle in High School Math Competitions](https://mlsanity.com/paper/2510.26768/) (2025)
- [Nemotron-Math: Efficient Long-Context Distillation of Mathematical Reasoning from Multi-Mode Supervision](https://mlsanity.com/paper/2512.15489/) (2025)
- [Dual-Space Knowledge Distillation for Large Language Models](https://mlsanity.com/paper/2406.17328/) (2024)
- [On the Geometry of On-Policy Distillation](https://mlsanity.com/paper/2606.07082/) (2026)
- [HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?](https://mlsanity.com/paper/2509.07894/) (2025)
- [SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation](https://mlsanity.com/paper/2605.07711/) (2026)
- [Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping](https://mlsanity.com/paper/2502.11104/) (2025)
- [P1: Mastering Physics Olympiads with Reinforcement Learning](https://mlsanity.com/paper/2511.13612/) (2025)
- [Cross-Tokenizer LLM Distillation through a Byte-Level Interface](https://mlsanity.com/paper/2604.07466/) (2026)
- [Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling](https://mlsanity.com/paper/2605.13301/) (2026)
- [P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads](https://mlsanity.com/paper/2602.09443/) (2026)
- [MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling](https://mlsanity.com/paper/2606.13473/) (2026)

## Built on by (most cited first, 6 of 6)

- [When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation](https://mlsanity.com/paper/2609.20511/) (2026)
- [Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening](https://mlsanity.com/paper/2609.18708/) (2026)
- [Solving Without Stopping: On-Policy Distillation at Small Scale](https://mlsanity.com/paper/2609.37326/) (2026)
- [Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition](https://mlsanity.com/paper/2609.14708/) (2026)
- [Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective](https://mlsanity.com/paper/2610.03185/) (2026)
- [Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation](https://mlsanity.com/paper/2610.13521/) (2026)

## Abstract (arXiv)

On-policy distillation (OPD) offers a promising way to transfer reasoning capabilities from stronger teacher models, but applying it to long-context reasoning teachers and short-context students introduces practical challenges, including tokenizer mismatch, teacher-student distribution mismatch, response length explosion, and training instability. In this work, we study this setting by transferring proof-reasoning capabilities from the long-context reasoning model SU-01 to short-context student models. To handle tokenizer differences, we perform OPD in a shared text space and align only tokens that occupy identical text spans under the student and teacher tokenizers. To mitigate the problem of excessive generation length and frequent truncation, we introduce a student reference KL loss and mask the advantages of special termination tokens such as </think> and <|im_end|>. This strategy constrains the student from drifting excessively from its initial policy, thereby mitigating the teacher-student distribution mismatch problem and fostering steady length growth. Experiments on both same-family and different-family student models, including Qwen3, Qwen3.5, Intern-S2, GLM-4.7, Gemma-4, show consistent gains in mathematical reasoning, especially natural-language math proving. Notably, Intern-S2-Preview improves by 21.2 points on ProofBench, reaching 55.2 and surpassing Gemini-2.5-Pro. It also improves on science benchmarks such as HLE and HiPhO, suggesting that OPD transfers reasoning capabilities that generalize beyond the mathematical training domain.