The paper investigates data efficiency and selection in On‑Policy Distillation (OPD) for large language models. It shows that 1‑shot OPD—training on a single example—consistently improves performance, especially when the example is hard, and that longer chain‑of‑thought (CoT) paths drive the gains rather than token entropy. Based on these findings, the authors propose a simple hard‑example selection strategy that, using only eight carefully chosen hard examples, matches the performance of a 17,000‑example baseline across models from 1.5B to 7B parameters.
By Zhinan Hou, Jiaqi Zhang, Xunliang Cai, Keyou You
arXiv:2607.22629v3 Announce Type: replace
Abstract: Large Reasoning Models produce long, explicit chains of intermediate steps before generating a final answer at inference time. These intermediate t...
By Durgesh Kalwar, Vardhan Palod, Jaya Adithya Pavuluri, Subbarao Kambhampati
arXiv:2605.13165v2 Announce Type: replace
Abstract: Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking. This inefficiency is espe...
By Chenjun Xu, Zhennan Zhou, Zhan Su, Bill Howe, Lucy Lu Wang, Bingbing Wen
The paper reports that in on‑policy distillation for large language models, reasoning performance can be improved by supervising only a tiny fraction of generated tokens—sometimes just one or two tokens per reasoning trajectory, about 0.05% of all tokens. This sparse supervision consistently matches or exceeds full‑token training across nine teacher‑student setups on mathematical reasoning, and is also validated on coding reasoning, Llama models, and PPO‑based reinforcement learning with verifiable reward. The findings suggest that effective post‑training does not require token‑intensive supervision and may align more closely with natural learning processes that focus on critical reasoning steps.
By Zhishuai Liu, Xingzi Xu, Mehmet Saygin Seyfioglu, Pan Xu, Karim Bouyarmane
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
arXiv:2605.10889v2 Announce Type: replace-cross
Abstract: On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions...
By Mohammadreza Armandpour, Fatih Ilhan, David Harrison, Ajay Jaiswal, Duc N. M Hoang, Fartash Faghri, Yizhe Zhang, Minsik Cho, Mehrdad Farajtabar
arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.
By Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati
arXiv:2608.29623v1 Announce Type: cross
Abstract: Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning...
By Yangsong Lan, Renkai Hu, HongKai Zheng, Bo Zhang, Renzhi Wang, Hongliang Dai, Piji Li
arXiv:2606. 31048v1 Announce Type: cross Abstract: This paper investigates knowledge distillation from a large reasoning model (DeepSeek-R1) to a compact student model (Qwen2.
By Gaurab Baral, Aaditya Khanal, Yangyang Tao, Junxiu Zhou
arXiv:2609.33455v2 Announce Type: replace
Abstract: On-policy distillation (OPD) trains a student model on its own trajectories using dense token-level feedback from a stronger teacher model. Since e...
By Zizhuo Lin, Quanling Liu, Yi Yang, Yawei Luo
arXiv:2606. 05988v1 Announce Type: new Abstract: Reasoning models produce long chain-of-thought traces that are costly to distill and encourage verbose student outputs.
By Maxime Griot, Paul Steven Scotti, Tanishq Mathew Abraham
arXiv:2605.10194v2 Announce Type: replace
Abstract: On-policy self-distillation (OPSD) uses a model as its own teacher under privileged context, providing token-level supervision on the model's own r...
By Jiaxuan Wang, Xuan Ouyang, Zhiyu Chen, Yulan Hu, Lan-Zhe Guo