The paper proposes Mixture Proposal On-Policy Distillation (MPOPD) to address a mismatch issue in on‑policy distillation (OPD) where the rollout policy is fixed to the current student. By treating the rollout policy as an optimization target, MPOPD derives a geometric mixture of student and teacher policies and introduces a proposal policy for efficient rollout generation. Experiments on 16 reasoning benchmarks show consistent gains over OPD, notably a 6.91% accuracy improvement on math reasoning with Qwen3-4B-Base and a 41% reduction in generation length.
By Sirui Chen, Yunzhe Qi, Haobo Xu, Jiaru Zou, Mengting Ai, Zihao Li, Jingrui He
The paper introduces a recursive self-improvement framework for language models that replaces an external teacher with a frozen copy of the student, enabling dynamic co-evolution (DCE) and self-refined concise learning (SRCL). DCE allows the privileged teacher to evolve alongside the student, while SRCL trains on shorter, verified rewrites to reduce verbosity. Experiments show that the combined DCE+SRCL approach outperforms traditional on‑policy self‑distillation across multiple model sizes and math benchmarks, achieving significant accuracy gains and shorter outputs.
By Shangjian Yin, Zehao Zhao, Kavosh Asadi, Rui Liu, Yuchen Lu, Shike Mei, Hang Cui, Luke Simon, Zhouxing Shi, Hamed Firooz
State-OPD introduces a state‑grounded on‑policy distillation framework that separates the objective task and action‑observation record from the student’s internal reasoning trajectory. By removing prior student reasoning and resampling complete reasoning‑action responses at high‑entropy states, the method improves teacher supervision and action diversity. Evaluations on ALFWorld, ScienceWorld, and WebShop show State‑OPD achieves the highest macro‑average success rates for Qwen3‑1.7B and Qwen3‑4B students, even surpassing a larger teacher model on certain tasks.
By Zhentao Zhang, Yanzhao Zheng, Yanlin Liu, Yuanqiang Yu, Tianze Xu, Chao Ma, Jihuai Zhu, Lelun Wu, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu
arXiv:2605. 07804v3 Announce Type: replace-cross Abstract: On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models.
By Zhicheng Yang, Zhijiang Guo, Yifan Song, Minrui Xu, Yongxin Wang, Yiwei Wang, Xiaodan Liang, Jing Tang
The paper introduces Selective Supervision for Direct-OPD (S$^2$D-OPD), a refinement of Direct On-Policy Distillation that filters out states where the teacher’s policy change is minimal, as measured by the teacher‑reference Jensen‑Shannon divergence. By masking low‑divergence states and keeping only the top 10% of states per response, S$^2$D-OPD improves held‑out accuracy on AIME and HMMT benchmarks across multiple teacher‑student pairs without additional forward passes.
By Yibo Zhao, Zixuan Yang, Yunshi Lan, Xiang Li
Bridged Self-Distillation (BSD) is a unified framework that enables on‑policy distillation from any teacher providing reasoning traces. The external teacher supplies a privileged reasoning trace offline, while a self‑teacher—an identical copy of the student conditioned on that trace—scores the student’s rollouts in its own token space. BSD uses these token‑level signals, along with a verifier, to adjust updates on unsuccessful rollouts, allowing the same training procedure to work with shared‑tokenizer, cross‑tokenizer, and closed‑API teachers and consistently outperforming scenario‑specific baselines.
By Runsheng Chen, Yihong Liu, Raoyuan Zhao, Michael A. Hedderich, Hinrich Sch\"utze, Matthias Grabmair
The paper introduces Multi-Teacher Self-Distillation Policy Optimization (MT‑SDPO), an on‑policy distillation method that combines multiple frozen teachers into a single student model. MT‑SDPO uses self‑anchors, answer‑verified eligibility, and privileged distillation to select reliable teachers per sample rather than per domain. Experiments on five students from three model families show that MT‑SDPO improves the weakest domain of Qwen3‑8B by 14.79 points and reduces its domain gap by 74.7%, achieving a more balanced performance than matching a single teacher to each domain.
By Xixiang He, Xingming Li, Baiqi Wu, Qiyao Sun, Xuanyu Ji, Ao Cheng, Qingyong Hu
arXiv:2607. 04037v1 Announce Type: cross Abstract: On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the teacher provides dense token-level supervision on the states the student actually visits.
By Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi, Chanakya Ekbote, Sujay Sanghavi, Aleksandar Bojchevski
Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck.
arXiv:2607. 26246v1 Announce Type: new Abstract: On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabilities across LLMs.
By Fangxu Yu, Zinan Lin, Xiaodong Liu, Weijia Xu, Michael Xu, Tianyi Zhou, Jianfeng Gao
arXiv:2610.14022v1 Announce Type: cross
Abstract: On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains co...
By Yingdong Shi, Zhihong Li, Changming Li, Jingyi Yu, Quan Li, Kan Ren
arXiv:2609.39687v1 Announce Type: new
Abstract: On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises studen...
By Xincheng Wei, Yifan Ding, Yoshua Li, Yuquan Lu, Ziheng Li, Yi Lu, Dongsheng Ma, Rongxiang Weng, Xunliang Cai