# Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning

arXiv: https://arxiv.org/abs/2605.11458 · HTML: https://mlsanity.com/paper/2605.11458/

## Key facts

- Cited by 14 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 23 of its 32 references that are in the map.
- First posted on arXiv 12 May 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, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [OpenThoughts: Data Recipes for Reasoning Models](https://mlsanity.com/paper/2506.04178/) (2025)
- [Self-Distillation Enables Continual Learning](https://mlsanity.com/paper/2601.19897/) (2026)
- [Entropy-Aware On-Policy Distillation of Language Models](https://mlsanity.com/paper/2603.07079/) (2026)
- [DistiLLM: Towards Streamlined Distillation for Large Language Models](https://mlsanity.com/paper/2402.03898/) (2024)
- [Curriculum Temperature for Knowledge Distillation](https://mlsanity.com/paper/2211.16231/) (2022)
- [RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold](https://mlsanity.com/paper/2406.14532/) (2024)
- [Hindsight Credit Assignment for Long-Horizon LLM Agents](https://mlsanity.com/paper/2603.08754/) (2026)
- [HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation](https://mlsanity.com/paper/2603.23871/) (2026)
- [GATES: Self-Distillation under Privileged Context with Consensus Gating](https://mlsanity.com/paper/2602.20574/) (2026)
- [Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning](https://mlsanity.com/paper/2601.09088/) (2026)
- [SODA: Semi On-Policy Black-Box Distillation for Large Language Models](https://mlsanity.com/paper/2604.03873/) (2026)
- [Adaptive Temperature Based on Logits Correlation in Knowledge Distillation](https://mlsanity.com/paper/2503.09030/) (2025)
- [Dynamic Temperature Scheduler for Knowledge Distillation](https://mlsanity.com/paper/2511.13767/) (2025)

## Built on by (most cited first, 14 of 14)

- [RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation](https://mlsanity.com/paper/2606.11709/) (2026)
- [Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning](https://mlsanity.com/paper/2608.01589/) (2026)
- [Rethinking Privileged Information in On-Policy Self-Distillation](https://mlsanity.com/paper/2608.18271/) (2026)
- [Matching Supervision to the Student's Learning Capacity: A Unified Framework for On-Policy Self-Distillation](https://mlsanity.com/paper/2608.08176/) (2026)
- [What Should a Self-Teacher See? Privileged Context Design for On-Policy Self-Distillation](https://mlsanity.com/paper/2609.25623/) (2026)
- [Activation-Conditioned Self-Distillation](https://mlsanity.com/paper/2609.38342/) (2026)
- [SR-OPSD: Self-Referenced On-Policy Self-Distillation](https://mlsanity.com/paper/2608.09745/) (2026)
- [One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation](https://mlsanity.com/paper/2608.25936/) (2026)
- [iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs](https://mlsanity.com/paper/2609.24646/) (2026)
- [E2-OPSD: Taming Entropy Overshoot in On-Policy Self-Distillation](https://mlsanity.com/paper/2610.05048/) (2026)
- [ReTeach: Building a Self-Teacher through Multi-Round Reflection and Retry](https://mlsanity.com/paper/2610.11529/) (2026)
- [PreSO: Privileged Representation Isolation for On-Policy Self-Distillation](https://mlsanity.com/paper/2610.14001/) (2026)
- [Self-Distillation with Verbal Regularization](https://mlsanity.com/paper/2610.16354/) (2026)
- [Teach Me After You Learn It: Lookahead Self-Distillation for RLVR](https://mlsanity.com/paper/2610.18256/) (2026)

## Abstract (arXiv)

On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own rollouts while conditioning on the reference solution. A design choice shared by nearly all such methods, however, has gone unquestioned: the teacher always sees the full reference reasoning. We argue that this default itself is part of the problem and identify a teacher-side exposure mismatch: when the teacher conditions on reasoning far beyond the student's current competence, the resulting token targets become too strong to absorb. A controlled fixed-exposure sweep makes this concrete on two fronts: 1) full exposure is not reliably the best choice, and 2) student-teacher mismatch grows monotonically as the teacher sees more privileged reasoning. This motivates treating teacher exposure not as a fixed hyperparameter but as a learnable training-time control variable. We therefore propose Adaptive Teacher Exposure for Self-Distillation (ATESD). ATESD models the reveal ratio with a lightweight Beta-policy controller conditioned on compact training-state statistics, and uses one sampled exposure for a short hold window of student updates. To make this exposure controller learnable, we optimize it with a discounted learning-progress reward that scores each held decision by its effect on the student's future improvement rather than its immediate loss change, addressing the delayed credit assignment induced by on-policy distillation. Experiments on AIME 24, AIME 25, and HMMT 25 across Qwen3-{1.7B, 4B, 8B} show that ATESD consistently outperforms competitive self-distillation and RL baselines, improving over OPSD by +0.95, +2.05, and +2.33 Average@12 points respectively, and establishing adaptive teacher exposure as an effective new axis for reasoning self-distillation.