The paper introduces Tail‑Corrected Top‑k On‑Policy Distillation (TT‑OPD), a method that improves on existing Top‑k OPD by combining the selected top‑k tokens with a sampled token from the student’s rollout. This hybrid approach recovers the probability mass discarded by limiting to top‑k, yielding an unbiased estimator of the reverse KL divergence gradient while maintaining low computational cost. Experiments show TT‑OPD outperforms other OPD variants in accuracy.
By Linjian Meng, Siyuan Gan, YuHan Li, Xiran Wang, Ziyang Ding, Ditang Gou, Yiming Wu, Zhen Zhao
arXiv:2609.37500v1 Announce Type: new
Abstract: On-policy distillation (OPD) trains language models using dense token-level teacher supervision on student-generated trajectories. However, its relianc...
By Yuxiao Yang, Shangzhe Li, Tianrun Yu, Kaixiang Zhao, Taylor W. Killian, Weitong Zhang
arXiv:2606. 22600v2 Announce Type: replace-cross Abstract: On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers.
By Yan Xie, Sijie Zhu, Tiansheng Wen, Bo Chen, Yifei Wang
arXiv:2610.19145v1 Announce Type: new
Abstract: On-policy distillation (OPD) is increasingly studied as a cheaper alternative to reinforcement learning, yet it remains a form of knowledge distillatio...
By Yiping Li, Fan Zhao, Zhibo Hou, Zhiyu An, Wan Du
arXiv:2605.07865v2 Announce Type: replace-cross
Abstract: On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for Large Language Models, especially in reasoning domains. How...
By Minjae Oh, Sangjun Song, Gyubin Choi, Yunho Choi, Yohan Jo
arXiv:2605. 03677v2 Announce Type: replace Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models into a single student model.
By Wenjin Hou, Shangpin Peng, Weinong Wang, Zheng Ruan, Yue Zhang, Zhenglin Zhou, Mingqi Gao, Yifei Chen, Kaiqi Wang, Hongming Yang, Chengquan Zhang, Zhuotao Tian, Han Hu, Yi Yang, Fei Wu, Hehe Fan
arXiv:2606. 08432v1 Announce Type: new Abstract: On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollouts.
By Li Jiang, Haoran Xu, Yichuan Ding, Amy Zhang
Activation-Conditioned Self-Distillation (ACSD) is a new on‑policy self‑distillation method that uses a frozen copy of the base model to extract a steering vector by contrasting activations from self‑generated trajectories that reach verified correct answers with all other trajectories. The student learns from next‑token distributions on its own prefixes, without needing reference text or teacher parameter updates, and is used alone at inference. Across five models, ACSD achieves the highest mean accuracy on four mathematical benchmarks, with notable gains on DeepSeek‑R1‑0528‑Qwen3‑8B and LiveCodeBench v6 compared to the OPSD baseline.
By Zhexi Lu, Subhajit Chaudhury, Tejaswini Pedapati, Keerthiram Murugesan, Lei Yu
The paper investigates whether on‑policy distillation (OPD) is always advantageous for transferring knowledge from a teacher to a student model. It introduces Semi‑OPD, which uses offline rollouts from the initial student, and demonstrates that across 17 teacher‑student pairs (1.5B–235B parameters) Semi‑OPD outperforms OPD in 14 cases, achieving up to +13.6% accuracy and an 11.4× speedup. The authors show that the benefit of OPD depends on the alignment between teacher and student, measured by an output‑token overlap ratio, and argue that effective distillation requires on‑policy behavior relative to both models.
By Siyan Zhao, Yonggan Fu, Jindong Jiang, Shih-Yang Liu, Song Bian, Byung-Kwan Lee, Sharath Turuvekere Sreenivas, Wenliang Dai, Hanrong Ye, Aditya Grover, Pavlo Molchanov
The paper investigates how the sampled-token reverse-KL loss in on‑policy distillation distributes updates across tokens. By analyzing the gradient of the per‑token K2 estimator, the authors find that tokens with low student probability and large teacher‑student gaps receive disproportionately large gradient norms. They propose Surprise‑aware Reweighting (SuRe), a lightweight weighting rule that further amplifies this allocation, and demonstrate that SuRe improves math metrics on Qwen3 student models without harming out‑of‑domain performance.
By Bing Shao, Jiazheng Zhang, Long Ma, Yujiong Shen, Senjie Jin, Xin Guo, Yuming Yang, Mingxu Chai, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang
On-policy distillation (OPD) is increasingly studied as a cheaper alternative to reinforcement learning, yet it remains a form of knowledge distillation (KD) that relies on teacher supervision. We rev...
arXiv:2609.36734v1 Announce Type: new
Abstract: Knowledge Distillation (KD) trains a smaller-capacity student model to imitate a larger-capacity teacher model by matching output distributions, implic...
By Ayan Sengupta, Vaibhav Seth, Tanmoy Chakraborty