English
Related papers

Related papers: Revisiting On-Policy Distillation: Empirical Failu…

200 papers

On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critical flaw: as the student's generated prefix inevitably diverges from the teacher's thought…

Machine Learning · Computer Science 2026-05-29 Zhicheng Yang , Zhijiang Guo , Yifan Song , Minrui Xu , Yongxin Wang , Yiwei Wang , Xiaodan Liang , Jing Tang

Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces…

Machine Learning · Computer Science 2026-05-26 Changyu Chen , Xiting Wang , Rui Yan

We study {on-policy self-distillation} (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories. Despite the performance gains of OPSD, we identify a…

Machine Learning · Computer Science 2026-05-13 Yuxiao Yang , Xiaoyun Wang , Weitong Zhang

On-policy distillation (OPD) is an effective post-training paradigm for large language models but requires a live teacher server throughout training, resulting in substantial infrastructure overhead. We investigate whether OPD can be…

Machine Learning · Computer Science 2026-05-11 Yecheng Wu , Song Han , Hai Cai

On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit assignment notoriously difficult. On-Policy Distillation (OPD)…

Machine Learning · Computer Science 2026-04-14 Binbin Zheng , Xing Ma , Yiheng Liang , Jingqing Ruan , Xiaoliang Fu , Kepeng Lin , Benchang Zhu , Ke Zeng , Xunliang Cai

On-policy distillation (OPD), which supervises a student on its own sampled trajectories, has emerged as a data-efficient post-training method for improving reasoning while avoiding the reward dependence of reinforcement learning and the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Ke Zhang , Yunjie Tian , Dongdi Zhao , Yijiang Li , Yuanye Liu , Vishal M Patel , Di Fu

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learning from verifiable rewards (RLVR). Existing OPD methods…

On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and student predictions are comparable token by token, an assumption that fails whenever the two…

Computation and Language · Computer Science 2026-05-22 Jie Sun , Mao Zheng , Mingyang Song , Qiyong Zhong , Yilin Cheng , Bichuan Feng , Pengfei Liu , Junfeng Fang , Xiang Wang

On-policy knowledge distillation (OPD) trains a student on its own rollouts under token-level supervision from a teacher. Not all token positions matter equally, but existing views of token importance are incomplete. We ask a direct…

Machine Learning · Computer Science 2026-05-22 Yuanda Xu , Hejian Sang , Zhengze Zhou , Ran He , Zhipeng Wang , Alborz Geramifard

On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that structured semantic rubrics can serve as a scalable alternative to…

Machine Learning · Computer Science 2026-05-11 Junfeng Fang , Zhepei Hong , Mao Zheng , Mingyang Song , Gengsheng Li , Houcheng Jiang , Dan Zhang , Haiyun Guo , Xiang Wang , Tat-Seng Chua

On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the…

Machine Learning · Computer Science 2026-05-07 Xin Yu , Liuchen Liao , Yiwen Zhang , Yingchen Yu , Lingzhou Xue , Qinzhen Guo

On-policy distillation (OPD) is an increasingly important paradigm for post-training language models. However, we identify a pervasive Scaling Law of Miscalibration: while OPD effectively improves task accuracy, it systematically traps…

Machine Learning · Computer Science 2026-04-21 Jiaxin Zhang , Xiangyu Peng , Qinglin Chen , Qinyuan Ye , Caiming Xiong , Chien-Sheng Wu

Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions. Yet these methods remain offline supervised…

Machine Learning · Computer Science 2026-05-27 Zhenglin Wan , Jingxuan Wu , Xingrui Yu , Chubin Zhang , Mingcong Lei , Bo An , Ivor W. Tsang , Yang You

Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model capacity. While reinforcement learning methods like group relative policy optimization…

Computation and Language · Computer Science 2026-05-11 Qiyong Zhong , Mao Zheng , Mingyang Song , Xin Lin , Jie Sun , Houcheng Jiang , Xiang Wang , Junfeng Fang

On-policy distillation is pivotal for transferring reasoning capabilities to capacity-constrained models, yet remains prone to instability and negative transfer. We show that on-policy distillation can be interpreted, both theoretically and…

Machine Learning · Computer Science 2026-03-13 Jongwoo Ko , Sara Abdali , Young Jin Kim , Tianyi Chen , Pashmina Cameron

On-Policy Self-Distillation (OPSD) is a unified learning framework in which a single large language model acts simultaneously as both teacher and student. Unlike conventional knowledge distillation that relies on a separate, often larger…

Human-Computer Interaction · Computer Science 2026-05-22 Fangming Cui , Sunan Li , Jiahong Li

Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system efficiency, but structurally deviates from the ideal on-policy objective. To address this…

Machine Learning · Computer Science 2026-05-19 Xianwei Chen , Shimin Zhang , Jibin Wu

On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. We observe that standard on-policy distillation can improve a student's output quality…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Ruiqi Liu , Xiaolei Lv , Gengsheng Li , Ximo Zhu , Zhiheng Wang , Zhengbo Zhang , Junkai Chen , Zhiheng Li , Bo Li , Jun Gao , Shu Wu

On-policy distillation has recently emerged as a promising alternative to standard sequence-level imitation, training a student by scoring its own rollouts with a teacher model. However, we observe ``Off-policy Teacher Decay'' problem in…

Machine Learning · Computer Science 2026-05-27 Zhou Ziheng , Jiaqi Li , Huacong Tang , Ying Nian Wu , Demetri Terzopoulos

On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and more stable supervision, while the parameter-level…

Computation and Language · Computer Science 2026-05-22 Yuchen Cai , Ding Cao , Liang Lin , Chunxi Luo , Xin Xu , Kai Yang , Weijie Liu , Saiyong Yang , Tianxiang Zhao , Guangzhong Sun , Guiquan Liu , Junfeng Fang