method · first seen 4 Oct 2026
on-policy self-distillation
Also: OPSD
Training a model by distilling from a teacher that is the same model given privileged information, using on-policy rollouts.
Mentions per week
PapersCodeDiscussion
Earliest sources
- E$^2$-OPSD: Taming Entropy Overshoot in On-Policy Self-DistillationPapers · 4 Oct 2026 · Yifei Liu, Minghao Fang, Xinyu Gu, Chengkai Yao, Mengdi Liu, Tengfei Ma, Jiangbi…
- Outcome-Guided On-Policy Self-DistillationPapers · 4 Oct 2026 · ZheXu Wang, Mao-Lin Luo, Yankun Hong, Zi-Hao Zhou, Bo Ye, Jian Zhao, Xialiang To…
- Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual ReasoningPapers · 4 Oct 2026 · Shinichi Uemura, Taiji Suzuki
- Off-Policy Merging Beats On-Policy Self-Distillation for Continual LearningPapers · 5 Oct 2026 · Chen Henry Wu, Thomas Zhang, Aditi Raghunathan
- You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn DialoguePapers · 5 Oct 2026 · Junle Chen, Wei Chen, Zhengjun Huang, Zhoujin Tian, Yuxuan Liu, Kai Wang, Rui Ch…
- Privileged Context as Drift in On-Policy Self-DistillationPapers · 6 Oct 2026 · Ravenor Davion, Nick Rui
Latest sources
- Learning When to Continue and When to Stop: Termination-Aware OPSDPapers · 15 Nov 2026 · Chaoqun He, Wannian Yi, Changyi Sun, Chaojun Xiao, Lijie Wen
- B-OPSD: On-Policy Self-Distillation with Self-Generated Problem BriefsPapers · 14 Nov 2026 · Zhi Xu, Yinqi Wu, Feng Zhang, Xiaotong Zhang, Hong Yu, Han Liu
- Simplify, Agree, Distill: Label-Free Self-Distillation with Stepping StonesPapers · 13 Nov 2026 · Dingyang Chen, Jinfeng Xiao, Zhenyu Zhang, William Hu, Ziyu Wang, Yang Liu, Shir…
- Turning Multi-Agent Communication into Token-Level Credit with On Policy Self DistillationPapers · 12 Nov 2026 · Zixu Wang, Yu Zhao, Xing Zheng, Bingbing Xu, Tian Xueyun, JiaTang Luo, Weiqiang…
- Privileged Information Does Not Guarantee Privileged Guidance: Auditing On-Policy Self-Distillation for Reasoning ModelsPapers · 11 Nov 2026 · Haoyi Qiu, Akshat Agarwal
- Prior-as-Skill: Remember Outside and Read Inside with On-Policy Self-Distillation for Self-Evolving VLM AgentsPapers · 11 Nov 2026 · Yan Lin, Jingyu Sun, Yifei Qian, Zhengtao Yao, Yuxia Wang, Daizong Liu, Chun Pon…
- Bootstrapped On-Policy DistillationPapers · 10 Nov 2026 · Yue Wu, Xueyu Zhou, Yangrong Hu, Jian Huang
- PhysOPSD: Code as Privilege for Physically Plausible Video GenerationPapers · 9 Nov 2026 · Harold Haodong Chen, Rui Peng, Lingteng Qiu, Kejie Qiu, Chao Xu, Zilong Dong
- ECOS: Environment-Calibrated On-Policy Self-Distillation for Language AgentsPapers · 9 Nov 2026 · Chenhao Zhang, Zhongan Wang, Mingxuan Li, Hehe Fan, Zheng Zhu, Ming Li
- Watching Itself Watch: Self-Auditing Visual Reliance for Video ReasoningPapers · 9 Nov 2026 · Rohan Dugad, Mi Luo, Kristen Grauman
- Tiny Evidence Region Localization with Selective Contrastive On-Policy Self-DistillationPapers · 7 Nov 2026 · Yujuan Pang, Wenhao Xu, Yinglei Teng
- RuACT: Recovering Inactive Rubrics as Adaptive Critics and TeachersPapers · 6 Nov 2026 · Yijun Li, Zhengxi Lu, Zhipiao Liu, Jinzheng Yu, Xutao Weng, Jian Shao, Yongliang…
Mentioned together with
In the ledger
- 2026-W47 · baseline #8 · open