The paper introduces Teacher-Gated On-Policy Distillation (TGOPD), a method that verifies teacher reliability at the prompt level before applying dense supervision in on-policy distillation. TGOPD uses verifier-scored teacher probes to decide whether to route a prompt to dense OPD or to a verifier-grounded alternative. Experiments on 4B and 35B models across mathematics, code, and instruction tasks show TGOPD outperforms vanilla OPD and improves teacher GPU utilization from 9.8% to 78.9% in a 4B single-domain run.
By Zhiwei Zhang, Zechen Sun, Fei Zhao, Kang Peng, Bin Liang, Huayu Deng, Yao Hu, Kam-Fai Wong, Mu Chuan
arXiv:2606. 06021v1 Announce Type: new Abstract: On-policy distillation (OPD) supervises the student only in output space by matching next-token probabilities.
By Shenzhi Yang, Guangcheng Zhu, Bowen Song, Haobo Wang, Mingxuan Xia, Xing Zheng, Yingfan Ma, Zhongqi Chen, Weiqiang Wang, Gang Chen
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
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...
arXiv:2606. 15912v1 Announce Type: cross Abstract: Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large models whose inference cost is prohibitive in practice.
By Gengsheng Li, Mao Zheng, Mingyang Song, Ruiqi Liu, Tianyu Yang, Jie Sun, Qiyong Zhong, Haiyun Guo, Junfeng Fang, Dan Zhang, Jinqiao 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
Waypoint-OPD is a new on-policy distillation method that leverages an intermediate teacher checkpoint to compare early and late policy shifts in reinforcement learning. By gating the endpoint shift based on the directional agreement between these early and late shifts, the method suppresses conflicting updates and requires only one additional frozen-teacher scoring pass. Experiments with Qwen3-4B teachers and larger Qwen3 student models in mathematical and code reasoning tasks show that Waypoint-OPD consistently outperforms endpoint-only transfer across all six domain–student settings.
By Bingxi Hou, Guochao Jiang, Guofeng Quan, Weiqing Li, Wenfeng Feng, Guohua Liu, Yuewei Zhang
arXiv:2609.36246v1 Announce Type: new
Abstract: We present OLIVE (OnLine InterVEntion). At each iteration, the evolving student policy generates a new prefix, the teacher continues it autoregressivel...
By Haojin Wang, Dylan Zhang, Huaibo Chen, Suhao Yu, Yihang Sun, Zhanyang Jin, Jiaying Ye, Dianqi Li, Prasanna Sattigeri, Kamal Youcef-Toumi, Hao Peng
The paper introduces Stochastic Truncated On-Policy Distillation (STOPD), a method that speeds up on-policy distillation by randomly truncating student rollouts and correcting sampling bias with blockwise inverse-probability weighting. STOPD retains teacher feedback for every generated token and preserves the expected gradient of vanilla OPD while providing theoretical error bounds for common optimizers. Experiments show that STOPD cuts generated tokens by 25–48% and achieves 1.3–2.2× faster training without sacrificing accuracy.
By Zhengxin Zhang, Maosen Tang, Ning Wang, Changhao Li, Jingren Zhou, Bo Dai, Sainyam Galhotra, Alex Townsend, Claire Cardie
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...
The paper investigates on‑policy distillation (OPD), a method that trains a student model using its own rollouts while a teacher remains frozen, to see if it can help a student improve on problems it currently fails. Experiments with Qwen‑3 and Phi‑4 models on a competition‑mathematics benchmark show that OPD actually degrades performance when training focuses on failure cases, even though training loss (KL divergence) continues to drop. However, when OPD is applied to a broader set of problems, it improves accuracy by 4.6 percentage points, indicating that OPD works well when most training data contains correct student prefixes but can reinforce errors if the training regime concentrates on failures.
By Shuo Yang, Zheyu Zhang, Mahito Sugiyama, Gjergji Kasneci
arXiv:2608. 04419v1 Announce Type: cross Abstract: On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but standard reverse-KL training can assign insufficient probability to other plausible continuations.
By Zikun Qu, Min Zhang, Mingze Kong, Zhiwei Shang, Yikun Ban, Shuang Qiu, Zhongxiang Dai