arXiv AI October 21, 2026 By Zizhuo Lin, Quanling Liu, Jinsheng Quan, Chao Zhang, Yifan Zhu, Xing Shi, Jingtao Xu, Zhihui Li, Yawei Luo

Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models

Read the original on arXiv AI →

The Flow has not summarised this story yet — read it at arXiv AI.

arXiv Machine Learning

Aug 11

Adaptive Supervised Anchoring for On-Policy Self-Distillation

arXiv:2608. 07935v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student.

By Meilin Yang (Renmin University of China, Beijing, China), Zixuan Ding (Renmin University of China, Beijing, China), Jianhao Nie (Renmin University of China, Beijing, China), Weite Zhang (Renmin University of China, Beijing, China), Yuxin Zhang (Renmin University of China, Beijing, China), Zhiming Shao (Renmin University of China, Beijing, China), Li Yu (Renmin University of China, Beijing, China), Zhe Fu (Renmin University of China, Beijing, China)

llms efficiency benchmarks safety

arXiv AI

Aug 5

When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation

arXiv:2608. 03632v1 Announce Type: new Abstract: On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals.

By Yinuo Jiang, Yongjie Ye, Zhou Tao, Xiang Zhuang, Qiang Zhang, Huajun Chen, Tiankai Li

llms efficiency multimodal

arXiv AI

Jun 11

When Context Returns: Toward Robust Internalization in On-Policy Distillation

arXiv:2606. 11627v1 Announce Type: cross Abstract: Recent work has shown that on-policy distillation can internalize privileged context, such as system prompts or task hints, into a student model so that the context is no longer needed at inference time.

By Xun Wang, Ruishuo Chen, Zhuoran Li, Yu Chen, Longbo Huang

efficiency

arXiv Machine Learning

Sep 30

Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics

arXiv:2609.36608v1 Announce Type: new Abstract: On-policy distillation (OPD) trains multi-turn language agents with dense teacher supervision on student-generated responses. However, standard think-t...

By Zubin Zheng, Jiahao Wu, Shaofeng Zhang, Zhirui Zhang, Yew-Soon Ong, Shengcai Liu

agents efficiency benchmarks

Hugging Face Trending Papers

Aug 4

When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation

On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals. Recent selective OPD methods improve this process by prioritizing signals that are confident, informative, or learnable.

llms efficiency multimodal

arXiv AI

Jul 3

DemoPSD: Disagreement-Modulated Policy Self-Distillation

arXiv:2607. 02502v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access.

By Yunhe Li, Hao Shi, Wenhao Liu, Mengzhe Ruan, Hanxu Hou, Zhongxiang Dai, Shuang Qiu, Linqi Song

llms efficiency benchmarks

One email a morning, machine-written

Related stories

Adaptive Supervised Anchoring for On-Policy Self-Distillation

When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation

When Context Returns: Toward Robust Internalization in On-Policy Distillation

Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics

When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation

DemoPSD: Disagreement-Modulated Policy Self-Distillation