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
The paper introduces Multi-Teacher Self-Distillation Policy Optimization (MT‑SDPO), an on‑policy distillation method that combines multiple frozen teachers into a single student model. MT‑SDPO uses self‑anchors, answer‑verified eligibility, and privileged distillation to identify the most reliable teacher for each sample rather than relying on domain labels. Experiments on five students from three model families show that MT‑SDPO improves the weakest domain of Qwen3‑8B by 14.79 points and reduces its domain gap by 74.7%, achieving a better balance than matching a single teacher per domain.
The paper introduces Multi-Teacher Self-Distillation Policy Optimization (MT‑SDPO), an on‑policy distillation method that combines multiple frozen teachers into a single student model. MT‑SDPO uses self‑anchors, answer‑verified eligibility, and privileged distillation to select reliable teachers per sample rather than per domain. Experiments on five students from three model families show that MT‑SDPO improves the weakest domain of Qwen3‑8B by 14.79 points and reduces its domain gap by 74.7%, achieving a more balanced performance than matching a single teacher to each domain.
By Xixiang He, Xingming Li, Baiqi Wu, Qiyao Sun, Xuanyu Ji, Ao Cheng, Qingyong Hu
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
RetireOPD introduces a self-retiring on‑policy distillation method for agentic reinforcement learning. It first trains a skill‑conditioned teacher with environment rewards, then jointly trains a skill‑free student with RL and OPD, allowing the student to autonomously stop using the teacher when its performance aligns with the teacher’s. Experiments on Qwen2.5 models show significant gains in ALFWorld success rates and WebShop accuracy compared to RL baselines and the teacher itself.
By Yan Yu, Zhengxi Lu, Yizhou Liu, Yichen Pan, Aozhe Wang, Qipeng Chen, Hua Yang, Wenqi Zhang, Weiming Lu, Qianglong Chen, Yongliang Shen
The paper introduces a recursive self-improvement framework for language models that replaces an external teacher with a frozen copy of the student, enabling dynamic co-evolution (DCE) and self-refined concise learning (SRCL). DCE allows the privileged teacher to evolve alongside the student, while SRCL trains on shorter, verified rewrites to reduce verbosity. Experiments show that the combined DCE+SRCL approach outperforms traditional on‑policy self‑distillation across multiple model sizes and math benchmarks, achieving significant accuracy gains and shorter outputs.
By Shangjian Yin, Zehao Zhao, Kavosh Asadi, Rui Liu, Yuchen Lu, Shike Mei, Hang Cui, Luke Simon, Zhouxing Shi, Hamed Firooz
The paper introduces On-Policy Attention Self-Distillation (OPASD), a method that augments token-level supervision with solution-conditioned attention distillation for reasoning models. OPASD projects a privileged teacher’s attention onto student-visible positions, renormalizes the distribution, and aligns it with the student. Experiments on three model sizes and four math benchmarks show that OPASD improves accuracy by 4.98–8.40 percentage points, reduces generated tokens by 73.9%, cuts compute by 72.6%, and trains 1.53× faster compared to token-only distillation.
By Safaeid Hossain Arib, Rabeya Akter, Ismam Nur Swapnil, Md. Faiyaz Abdullah Sayeedi, Tasnim Mohiuddin, Md Mofijul Islam
arXiv:2609.08798v1 Announce Type: new
Abstract: Weak-to-strong generalization asks whether stronger models can learn from weaker supervisors and surpass them. This question is particularly important...
By Youngrok Park, Sangmin Bae, Hojung Jung, Jongwoo Ko, Yunseon Choi, Young Jin Kim, Pashmina Cameron, Aaron Courville, Se-Young Yun
DualOPSD introduces an asymmetric alternating framework for on-policy self-distillation, where a privileged teacher first trains the student and then adapts to the student’s updated distribution on the same trajectory, eliminating the need for additional rollouts. This adaptive approach improves average performance on AIME 2024, AIME 2025, and HMMT 2025 benchmarks for the Qwen3-8B model, with gains that vary by model scale. Across 1.7B, 4B, and 8B scales, DualOPSD also reduces truncation effects and lowers KL divergence between teacher and student.
By Yutong Chen, Guangfu Guo, Zhichao Xu, Kunpeng 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
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: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