CA-OPD is a confidence‑aware on‑policy distillation framework that improves structured visual prediction by using teacher confidence to selectively correct unreliable student transitions and gradually transfer rollout control to the student. The method aligns supervision with intervention decisions, providing direct cross‑entropy loss for corrected tokens and full predictive distribution for retained tokens. In a multi‑teacher setting for GUI grounding and OCR, CA‑OPD significantly outperforms the Qwen3.5‑0.8B baseline, achieving large gains on benchmarks such as ScreenSpot‑Pro and OCRBench‑v2 English.
By Menghao Li, Linjie Mu, Yin Wang, Haotian Hu, Yannian Gu, Lujiayi Xue, Fanyi Wang
The paper introduces Trajectory-only Adversarial Distillation (TAD), a method that distills vision‑language‑action policies using only teacher trajectory data without requiring teacher action scores. TAD employs a discriminator to compare feature marginals from teacher and student rollouts, providing adaptive rewards for on‑policy learning. In experiments on the ManiSkill task PutOnPlateInScene25Main, TAD significantly boosts OpenVLA‑OFT performance from 26.2% to 76.6% success‑once and from 20.3% to 58.6% success‑end, approaching white‑box on‑policy distillation while using fewer teacher queries and interaction budgets.
By Yun Zhu, Da Wang
The study compares supervised fine-tuning (SFT) and reinforcement learning (RL) as teacher training methods for on-policy distillation (OPD) in a single-teacher setting. Using Qwen3.5-9B models across Agentic, Reasoning, and Perception domains, RL-trained teachers consistently produce stronger students and better recovery of performance gains than SFT-trained teachers. The authors attribute this advantage to RL teachers’ smaller parameter shifts from the shared initialization, which facilitates learning through OPD.
By Jingyuan Huang, Zuming Huang, Yucheng Shi, Zhongzhi Li, Xiaoming Zhai, Wei Chu, Ninghao Liu
arXiv:2608. 16333v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories.
By Changhui Sun, Lanbo Liu, Hang Lei, Tong Ling, Jiahang Xie, Zhiyong Zheng, Yujia Wang, Hao Liu, Feng Xiao, Lu Liu, Yanlong Du, Zifeng Cheng, Ziwei Jiang, Qing Gu
The paper introduces Selective Supervision for Direct-OPD (S$^2$D-OPD), a refinement of Direct On-Policy Distillation that filters out states where the teacher’s policy change is minimal, as measured by the teacher‑reference Jensen‑Shannon divergence. By masking low‑divergence states and keeping only the top 10% of states per response, S$^2$D-OPD improves held‑out accuracy on AIME and HMMT benchmarks across multiple teacher‑student pairs without additional forward passes.
By Yibo Zhao, Zixuan Yang, Yunshi Lan, Xiang Li
The paper reviews On‑Policy Self‑Distillation (OPSD), a method where a language model learns from its own generations using privileged information such as reference solutions or plans, eliminating the need for a larger teacher model. It identifies a key failure mode—collapse, where the model’s reasoning paths narrow progressively—and analyzes it through three levers: signal application, privileged information, and teacher dynamics. The review focuses on mathematical reasoning, offering a unified vocabulary and distinguishing settled facts from ongoing debates.
By Justin Robert, Raheel Qader
On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories. This approach has achieved strong empirical gains and can often surpass conve...
The paper introduces a method for offline on‑policy distillation that addresses the problem of imperfect teacher supervision. By training on teacher‑successful problems and measuring changes in token likelihoods on teacher‑failed trajectories, the authors derive a learnability signal that weights the distillation loss. This approach improves performance on mathematical reasoning and code generation tasks while reducing computational cost compared to online distillation.
By Yihao Ai, Weilong Yan
arXiv:2610.14022v1 Announce Type: cross
Abstract: On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains co...
By Yingdong Shi, Zhihong Li, Changming Li, Jingyi Yu, Quan Li, Kan Ren
Offline on-policy distillation gains efficiency by collecting student trajectories and teacher supervision once and reusing them throughout optimization. The same reuse makes imperfect supervision per...
On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of imitation learning with the on-policy sampling of...
arXiv:2609.37522v1 Announce Type: new
Abstract: On-policy distillation (OPD) trains compact language agents with teacher feedback on student-generated trajectories. In multi-turn tasks, compounding e...
By Xiaohan Yi, Wen Luo, Yani Huang, Junfeng Zhan, Asher Qin, Peilin Zhao, Xi Xiao