The paper investigates how much training data is required for on‑policy distillation (OPD) of foundation models. It shows that in two single‑teacher settings, only eight real prompts can match the performance of 17,000 problems, and that 64 self‑generated questions can replace full external datasets. In multi‑teacher scenarios, 1,000 generated questions achieve comparable results to 7,000 real examples, while fully implicit question generation works only in limited cases.
By Gengsheng Li, Mao Zheng, Mingyang Song, Jie Sun, Zeyuan Liu, Ruiqi Liu, Tianyu Yang, Qiyong Zhong, Haiyun Guo, Junfeng Fang, Shiming Xiang, Jinqiao Wang, Tat-Seng Chua
BoundaryEvo introduces a two‑stage data‑model co‑evolution framework for distilling long‑chain reasoning from large teacher models into small language models. First, Capability Priming distills a small set of teacher trajectories to give the student an initial reasoning baseline. Then, Capability‑Boundary Co‑Evolution iteratively selects questions the student has not mastered but the teacher can solve, updating the training data as the student’s capability grows. With only 1,000 examples, BoundaryEvo improves Qwen3.5‑4B accuracy from 62.9 % to 75.3 % on IMO‑AnswerBench and from 26.8 % to 46.0 % on AMO‑Bench, outperforming static and dynamic baselines across 11 benchmarks.
By Jiaming Su, Suorong Yang, Xudong Li, Tengchao Yang, Peng Ye
arXiv:2512. 21002v3 Announce Type: replace-cross Abstract: Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data.
By Wei-Rui Chen, Vignesh Kothapalli, Ata Fatahibaarzi, Hejian Sang, Shao Tang, Qingquan Song, Zhipeng Wang, Muhammad Abdul-Mageed
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
The paper investigates on‑policy distillation (OPD) of large language models when trained on a minimal amount of data, specifically a single query. It finds that one‑shot OPD continues to improve for hundreds of steps and recovers most of the performance gains achieved with full‑dataset training across various tasks and model families. The authors attribute this to the high state coverage achieved early in training and show that adding a few semantically distinct queries further boosts coverage and accuracy, eventually matching full‑data results. They conclude that OPD is data‑overfed but algorithm‑starved, highlighting the need to focus on step efficiency and the underlying mechanisms of its recent successes.
By Zixuan Fu, Bingxiang He, Yuxin Zuo, Haohuan Huang, Jinqian Zhang, Ruhang Xiao, Cheng Qian, Qinyu Luo, Huan-ang Gao, Yudong Wang, Zhiyuan Liu, Ning Ding, Chaojun Xiao
arXiv:2508. 09883v2 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving.
By Xiaojun Wu, Xiaoguang Jiang, Huiyang Li, Jucai Zhai, Dengfeng Liu, Qiaobo Hao, Huang Liu, Zhiguo Yang, Ji Xie, Ninglun Gu, Jin Yang, Kailai Zhang, Yelun Bao, Jun Wang
OPDSearch+ introduces a two‑stage distillation framework for search‑augmented reasoning that eliminates the need for task‑specific teacher fine‑tuning. In the first stage, a frozen off‑the‑shelf instruct model guides a student through live search interactions using a per‑position forward KL objective, transferring reasoning decomposition and evidence integration skills. The second stage refines this student with reinforcement learning, achieving performance surpassing RL alone and outperforming all prior 3B‑parameter baselines on seven QA benchmarks, including 13.1% improvement on HotpotQA and 8.5% on 2WikiMultihopQA.
By Qinglin Ye, Zhiyuan Gu, Jingjie Xia, Yiheng Zhang, Kaiyan Zhao, Shunchao Zheng, Yuhang Mu, Wenchao Du, Yiming Wang
Search-augmented reasoning remains difficult for small language models. On-policy distillation (OPD) from trained teachers offers a promising direction, but suffers from two issues: (1) high-quality m...
arXiv:2608. 03632v1 Announce Type: new Abstract: On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals.
By Yinuo Jiang, Yongjie Ye, Zhou Tao, Xiang Zhuang, Qiang Zhang, Huajun Chen, Tiankai Li
arXiv:2608. 11829v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning.
By Xinmu Ge, Zizhuo Zhang, Yu Huang, Jianing Zhu, Lin Yuan, Wanli Gu, Weichang Wu, Weiran Huang, Xiaolu Zhang, Bo Han, Jun Zhou, Jiangchao Yao
arXiv:2605. 09253v2 Announce Type: replace-cross Abstract: While recent work in Reinforcement Learning with Verifiable Rewards (RLVR) has shown that a small subset of critical tokens disproportionately drives reasoning gains, an analogous token-level understanding of On-Policy Distillation (OPD) remains largely unexplored.
By Yuxuan Jiang, Runchao Li, Shubhashis Roy Dipta, Dawei Li, Zhao Yang
arXiv:2605. 15532v3 Announce Type: replace-cross Abstract: Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets.
By Jaehun Jung, Hyunwoo Kim, Brandon Cui, Ximing Lu, David Acuna, Prithviraj Ammanabrolu, Yejin Choi