# OSPD: On-Policy Self-Distillation for Persona-Consistent Dialogue

arXiv: https://arxiv.org/abs/2609.34418 · HTML: https://mlsanity.com/paper/2609.34418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in On-policy and self-distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- 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, 17 of 17)

- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [On-Policy Context Distillation for Language Models](https://mlsanity.com/paper/2602.12275/) (2026)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [Entropy-Aware On-Policy Distillation of Language Models](https://mlsanity.com/paper/2603.07079/) (2026)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [Privileged Information Distillation for Language Models](https://mlsanity.com/paper/2602.04942/) (2026)
- [Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2511.00222/) (2025)
- [GATES: Self-Distillation under Privileged Context with Consensus Gating](https://mlsanity.com/paper/2602.20574/) (2026)
- [Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?](https://mlsanity.com/paper/2404.12138/) (2024)
- [Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning](https://mlsanity.com/paper/2503.17662/) (2025)
- [ToDi: Token-wise Distillation via Fine-Grained Divergence Control](https://mlsanity.com/paper/2505.16297/) (2025)
- [Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning](https://mlsanity.com/paper/2506.01748/) (2025)
- [BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model](https://mlsanity.com/paper/2408.10903/) (2024)
- [MINDECHO: Role-Playing Language Agents for Key Opinion Leaders](https://mlsanity.com/paper/2407.05305/) (2024)
- [CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization](https://mlsanity.com/paper/2508.09074/) (2025)
- [Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents](https://mlsanity.com/paper/2503.08193/) (2025)

## Abstract (arXiv)

Maintaining persona consistency across multi-turn dialogues remains a core challenge for role-playing language models. Off-policy distillation from external teachers incurs distribution mismatch that compounds across dialogue turns, while reinforcement learning struggles with reward ambiguity inherent in subjective persona fidelity. We propose OSPD, an on-policy self-distillation framework where the same model serves as both teacher and student under asymmetric information: the teacher receives a complete character profile while the student sees only a brief summary, and the student generates trajectories from its own policy. We find that teacher confidence in role-playing dialogue exhibits a bimodal structure---sharply peaked at character-critical tokens yet diffuse at generic utterances---and introduce role-aware divergence switching to match this structure. A progressive trait masking curriculum further forces staged internalization of character knowledge along semantic dimensions. Experiments on CharacterBench, CharacterEval, and SocialBench show that OSPD substantially improves persona consistency over supervised fine-tuning and multi-turn RL baselines, without requiring any external teacher or reward model.