The paper proposes a reward‑density principle for language‑model post‑training: sparse sequence‑level rewards are best for exploring and discovering new behaviors in a strong teacher, while dense token‑level teacher supervision is optimal for compressing that behavior into a smaller deployment model. The authors validate this rule with a four‑stage workflow—teacher RL, forward‑KL warmup, on‑policy distillation, and optional post‑bridge student RL—showing that an RL‑improved 8B teacher distilled through a dense bridge outperforms direct GRPO on a 1.7B student across math and code benchmarks. Ablation studies confirm each stage’s contribution, and the approach generalizes to Llama and Qwen models, offering a practical guideline for allocating scarce labeled data.
By Yuanda Xu, Hejian Sang, Zhengze Zhou, Ran He, Zhipeng Wang, Alborz Geramifard
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 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:2608. 12957v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, but receives no useful relative signal when every sampled response is incorrect.
By Yubo Zhang, Xinhong Ma, Zezhong Tan, Ziqiang Dong
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
The paper introduces D$^3$-MOPD, a dynamic domain scheduling method for multi-teacher on‑policy distillation. It adapts the domain mixture during training by monitoring each domain’s reverse‑KL trajectory, thereby allocating more compute to slower‑converging domains and less to those that plateau early. Experiments on a Qwen3.6‑35B‑A3B student show that D$^3$-MOPD closes 97% of the student‑to‑teacher performance gap, matches peak performance with roughly three times fewer rollout steps, and outperforms specialist teachers on most benchmarks.
By Zechen Sun, Zhiwei Zhang, Fei Zhao, Juntao Li, Mu Chuan, Huayu Deng, Guojian Zhan, Wenliang Chen, Yao Hu, Min Zhang
arXiv:2610.08398v1 Announce Type: new
Abstract: On-policy distillation from multiple teachers combines expertise from different domains in a single student, but conflicting gradients can hinder this...
By Taojie Zhu, Jing Jin, Yuan Xia, Chenyang Ding, Qunshan He, Wanke Xia, Tao Sun, Yan Chen, Jian Wang, Jinjie Gu, Tao Feng
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
arXiv:2607. 26246v1 Announce Type: new Abstract: On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabilities across LLMs.
By Fangxu Yu, Zinan Lin, Xiaodong Liu, Weijia Xu, Michael Xu, Tianyi Zhou, Jianfeng Gao
arXiv:2606. 22600v2 Announce Type: replace-cross Abstract: On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers.
By Yan Xie, Sijie Zhu, Tiansheng Wen, Bo Chen, Yifei Wang
The paper introduces D$^3$-MOPD, a zero‑overhead scheduler that dynamically adjusts domain sampling ratios during multi‑teacher on‑policy distillation by monitoring per‑domain reverse‑KL signals. Unlike static mixtures, D$^3$-MOPD reallocates compute toward slower‑converging domains, improving efficiency and performance. In experiments with a Qwen3.6‑35B‑A3B student distilled from four domain‑expert teachers, the method closes 97% of the student‑to‑teacher gap, matches peak performance with roughly three times fewer rollout steps, and outperforms specialist teachers on most benchmarks.
By Zechen Sun, Zhiwei Zhang, Fei Zhao, Juntao Li, Mu Chuan, Huayu Deng, Guojian Zhan, Wenliang Chen, Yao Hu, Min Zhang
arXiv:2609.36546v1 Announce Type: cross
Abstract: On-policy distillation (OPD) trains a student model on its self-generated trajectories with dense token-level teacher feedback. However, naive OPD ma...
By Shutong Wu, Xiwen Chen, Brendan Rappazzo, Daiheng Zhang, Anderson Schneider, Yuriy Nevmyvaka, Jiawei Zhang