The paper introduces Group‑Calibrated On‑Policy Distillation (GC‑OPD), a method that aligns token‑level teacher guidance with trajectory‑level verifier rewards for long‑context reasoning tasks. GC‑OPD normalizes rewards within rollout groups, uses the signed teacher‑verifier disagreement as a residual, and distributes this residual across tokens via Relative‑Advantage‑Based Credit Assignment (RACA). Experiments on five long‑context benchmarks show that GC‑OPD improves Qwen3‑4B and Qwen3‑8B checkpoints from 29.08/35.12 to 40.47/44.65, outperforming vanilla OPD and demonstrating the effectiveness of group‑relative residual calibration.
By Zhu Zhang, Jixun Wang, Xiaoang Xu, Xiaorong Wang, Zihan Zhou, Zhiyuan Wang, Shuo Wang, Chaojun Xiao, Yuezhi Zhou
The paper investigates on‑policy distillation (OPD), showing that teacher supervision during OPD contains significant noise that grows with teacher size, yet the student policy remains largely unaffected by this noise. It finds that OPD’s gains stem mainly from suppressing low‑log‑probability tokens, a process that can be replicated without a teacher. Building on this insight, the authors propose On‑Policy Self‑Adaptation (OPSA), a supervision‑free method that uses entropy‑adaptive negative advantages to improve performance on several benchmarks, outperforming both the base model and OPD.
By Yi Ding, Ruqi Zhang
arXiv:2604. 10688v2 Announce Type: replace-cross Abstract: On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit assignment notoriously difficult.
By Binbin Zheng, Xing Ma, Yiheng Liang, Jingqing Ruan, Xiaoliang Fu, Kepeng Lin, Benchang Zhu, Ke Zeng, Xunliang Cai
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
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.
arXiv:2606. 29476v1 Announce Type: cross Abstract: Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged context.
By Zibin Meng, Kani Chen
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
SCOPE-OPSD introduces a Fisher‑conditioned privileged subspace for on‑policy self‑distillation (OPSD) that projects the teacher‑student residual onto a frozen rank‑64 factor derived from residual covariance and language‑model‑head Fisher sensitivity. The method adds no extra rollouts or inference modules and, across multiple Qwen3 model checkpoints and trajectory lengths, consistently matches or surpasses pure OPSD and a matched random baseline, achieving significant gains in most settings. A cross‑fitted diagnostic shows a 4.40‑fold increase in captured privileged‑gap compared to the random orientation.
By Yunmeng Chen (Chongqing Ant Consumer Finance Co., Ltd), Kunyu Wang (Alibaba Cloud Computing Co., Ltd), Peihan Li (Chongqing Ant Consumer Finance Co., Ltd), Yi Wang (Chongqing Ant Consumer Finance Co., Ltd), Shuyin Xia (Chongqing University of Posts and Telecommunications), Yi Liu (Chongqing Ant Consumer Finance Co., Ltd), Xinyong Cheng (Alibaba Cloud Computing Co., Ltd), Dehui Wang (Alibaba Cloud Computing Co., Ltd), Xiangyong Zhai (Alibaba Cloud Computing Co., Ltd), Yanxing Liu (Chongqing Ant Consumer Finance Co., Ltd), Song Liu (Chongqing Ant Consumer Finance Co., Ltd)
arXiv:2609. 03241v1 Announce Type: cross Abstract: A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse supervision, while dense same-model guidance can reinforce false confidence or overconcentrate learning on a narrow solution mode.
By Zixun Huang, Kishan Panaganti, Haitao Mi, Leowei Liang
arXiv:2606. 12634v1 Announce Type: cross Abstract: Long-horizon tool-use reinforcement learning can learn from outcome verification, but its trajectory-level advantage is broadcast across many reasoning, API, and answer tokens.
By Tianyu Ding, Jianhong Xin, Juan Pablo De la Cruz Weinstein
arXiv:2608. 09836v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repetitive loops to achieve near-perfect token agreement with the teacher despite globally flawed responses.
By Zichao Yu, Chengzhi Yu, Shengze Xu, Yujin Han, Bingqing Jiang, Xu Wang, Difan Zou
Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck.