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
arXiv:2607. 05394v1 Announce Type: cross Abstract: 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.
By Shiyuan Feng, Huan-ang Gao, Haohan Chi, Hanlin Wu, Zhilong Zhang, Zheng Jiang, Bingxiang He, Wei-Ying Ma, Ya-Qin Zhang, Hao Zhou
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.
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
RISE (Recursive Improvement via Self-Extrapolating Policy Distillation) is a new method that builds a synthetic teacher from a language model’s own RLVR training trajectory. By extrapolating the displacement between the current checkpoint and a trailing anchor in parameter or logit space, RISE transforms sparse outcome-based updates into dense token-level targets without external models or privileged conditioning. The approach recursively refines the student model, combining RLVR and on‑policy distillation, and demonstrates superior performance across mathematical reasoning, STEM, code generation, and multi‑turn agentic tasks.
By Yang Li, Semih Yavuz, Shafiq Joty
arXiv:2609.14636v1 Announce Type: new
Abstract: On-policy distillation (OPD) has become a standard approach for transferring capabilities from large teachers to compact students. Its cost, however, i...
By Zhiyu Gui, Kexin Huang, Jia Guo, Junkang Wu, Zihao Wang, Zhiqiang Zhang, Jun Zhou, Jiancan Wu, Xiang Wang
arXiv:2607. 18955v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation.
By Qiye Cai, Yichuan Ma, Linyang Li, Peiji Li, Yongkang Chen, Qipeng Guo, Yicheng Zou, Tao Gui, Xiaocheng Feng, Bing Qin
arXiv:2608. 09745v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, providing a useful complement to reinforcement learning with sparse outcome rewards.
By Zhuo Sun, Entong Li, Yanlong Zhao, Xiaoyuan Cheng, Wenxuan Yuan, Kaiyu Li, Che Liu, Huihang Liu, Harrison Bo Hua Zhu, Li Zeng
The paper investigates on‑policy distillation (OPD), showing that teacher supervision during OPD contains significant noise that grows with teacher size, yet the student policy remains largely unaffected by this noise. It finds that OPD’s gains stem mainly from suppressing low‑log‑probability tokens, a process that can be replicated without a teacher. Building on this insight, the authors propose On‑Policy Self‑Adaptation (OPSA), a supervision‑free method that uses entropy‑adaptive negative advantages to improve performance on several benchmarks, outperforming both the base model and OPD.
By Yi Ding, Ruqi Zhang
The paper reviews On‑Policy Self‑Distillation (OPSD), a method where a language model learns from its own generations using privileged information such as reference solutions or plans, eliminating the need for a larger teacher model. It identifies a key failure mode—collapse, where the model’s reasoning paths narrow progressively—and analyzes it through three levers: signal application, privileged information, and teacher dynamics. The review focuses on mathematical reasoning, offering a unified vocabulary and distinguishing settled facts from ongoing debates.
By Justin Robert, Raheel Qader
arXiv:2608. 07068v1 Announce Type: new Abstract: Long-horizon agents accumulate growing contexts during interaction, impairing performance and stability.
By Zhiyuan Liu, Tinghong Ye, Chenghao Liu, Yizhuo Li, Songfang Huang
The paper introduces Zone of Proximal Policy Optimization (ZPPO), a method that keeps a teacher model inside prompts rather than in the policy gradient to improve knowledge distillation for small students. ZPPO creates two types of reformulated prompts—Binary Candidate-included Questions (BCQ) and Negative Candidate-included Questions (NCQ)—to expose students to correct and incorrect responses, and uses a replay buffer to focus training on hard questions until the student’s accuracy improves. Experiments on the Qwen3.5 family with a 27B teacher across 31 benchmarks show that ZPPO outperforms both off‑policy and on‑policy distillation methods, especially at the smallest student scales.
By Byung-Kwan Lee, Ximing Lu, Shizhe Diao, Minki Kang, Saurav Muralidharan, Karan Sapra, Andrew Tao, Pavlo Molchanov, Yejin Choi, Yu-Chiang Frank Wang, Ryo Hachiuma