{
  "id": 18261,
  "url": "https://arxiv.org/abs/2608.09745v1",
  "title": "SR-OPSD: Self-Referenced On-Policy Self-Distillation",
  "summary": "On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, providing a useful complement to reinforcement learning with sparse outcome rewards. However, the self-teacher policy used in OPSD is typically a stop-gradient or exponential-moving-average copy of the policy conditioned on additional context information, and thus co-evolves with both the student policy and its on-policy context distribution. Directly m",
  "authors": "Zhuo Sun, Entong Li, Yanlong Zhao, Xiaoyuan Cheng, Wenxuan Yuan, Kaiyu Li, Che Liu, Huihang Liu, Harrison Bo Hua Zhu, Li Zeng",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T15:40:07.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/18261",
  "original_url": "https://arxiv.org/abs/2608.09745v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}