{
  "id": 4441,
  "url": "https://arxiv.org/abs/2605.12652v2",
  "title": "Multi-Rollout On-Policy Distillation via Peer Successes and Failures",
  "summary": "Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails. On-policy distillation (OPD) offers denser token-level supervision by training on student-generated trajectories, yet existing methods typically distill each rollout independently and ignore the other attempts sampled for the same prompt. We introduce Multi-Rollout On-Policy Distillation (MOPD), a pee",
  "authors": "Weichen Yu, Xiaomin Li, Yizhou Zhao, Xiaoze Liu, Ruowang Zhang, Haixin Wang et al.",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-12T18:57:44.000Z",
  "fetched_at": "2026-07-14T16:30:59.238Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4441",
  "original_url": "https://arxiv.org/abs/2605.12652v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}