The paper investigates how privileged information—such as a teacher’s full solution or reasoning trace—affects on‑policy self‑distillation (OPSD) in language models. Using the AMPLE‑Math benchmark, the authors compare distillation with and without extra teacher views, finding that reference‑free distillation explains most gains for Qwen3‑1.7B, while additional references provide modest benefits, especially for polished solutions. The study also shows that the impact of privileged data depends on the student’s training regime and that altering token‑level supervision can leave student behavior largely unchanged.
By XiuYu Zhang, Wei Chow, Junfeng Fang, Zhenkai Liang, Tat-Seng Chua
arXiv:2606. 30626v1 Announce Type: new Abstract: On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals.
By Xinlei Yu, Gen Li, Qingyi Si, Guibin Zhang, Yuqi Xu, Congcong Wang, Shuai Dong, Kaiwen Tuo, Xiangyu Zeng, Kaituo Feng, Qunzhong Wang, Yang Shi, Xiaobin Hu, Xiangyu Yue, Jiaqi Wang, Shuicheng Yan
arXiv:2609.37132v1 Announce Type: new
Abstract: On-policy self-distillation (OPSD) improves large language models by letting a self-teacher with privileged information provide dense token-level super...
By Zheng Zhang, Xinyue Tan, Lufei Li, Xinyi Zhang, Yexin Li, Kan Ren
arXiv:2608. 04794v1 Announce Type: new Abstract: Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it.
By Sarthak Harne, Chinmay Karkar, Yash Pandya, Ahmed Awadallah, Akshay Nambi
The paper investigates on‑policy self‑distillation (OPSD), where a student model learns from its own outputs using token‑level supervision conditioned on privileged reference information. Experiments with Qwen3 models on science and mathematics datasets show that the correct reference does not consistently improve performance; students can improve without it, and solutions from other problems sometimes outperform the correct reference. The study finds that student predictions align more closely with the base model’s reasoning than with the reference supervision, and that alignment alone does not reliably predict performance gains.
By Samyak Shrestha, Alexander Tessier
arXiv:2606. 05718v1 Announce Type: cross Abstract: On-policy distillation (OPD) improves reasoning by training a student on trajectories sampled from its own policy under supervision from a teacher.
By Kanghui Tian, Siyuan Liu, Ziang Yan, Sheng Xia, Shuai Dong, Yi Wang
arXiv:2607. 05184v1 Announce Type: new Abstract: Self-distillation is a promising recipe for self-improvement in language models.
By Simran Kaur, Narutatsu Ri, Yinghui He, Liam Fowl, Sanjeev Arora
arXiv:2608. 09228v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the target problem and supervises the student's trajectory.
By Yuki Ichihara, Naoto Iwase, Mohammad Atif Quamar, Junpei Komiyama
arXiv:2608. 09826v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63.
By Yubo Jiang, Fengying Xie, Zhiguo Jiang, Haopeng Zhang
arXiv:2607. 02502v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access.
By Yunhe Li, Hao Shi, Wenhao Liu, Mengzhe Ruan, Hanxu Hou, Zhongxiang Dai, Shuang Qiu, Linqi Song
arXiv:2609.21619v1 Announce Type: new
Abstract: On-policy distillation (OPD) improves reasoning models by learning the token-level discrepancy between a stronger teacher and an on-policy student. How...
By Qiangqiang He, Jin Li, MingCai Chen
Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63. 0-68.