{
  "id": 13009,
  "url": "https://arxiv.org/abs/2607.04763",
  "title": "Multi-Turn On-Policy Distillation with Prefix Replay",
  "summary": "We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn interaction histories. Fully online OPD is costly because each update requires fresh student rollouts through the environment and teacher queries at visited histories. We propose Replayed-Prefix On-Policy Distillation (ReOPD), an off-environment alternative that reuses pre-collected teacher trajectories as replayed pr",
  "authors": "Baohao Liao, Hanze Dong, Christof Monz, Xinxing Xu, Li Dong, Furu Wei",
  "category": "research",
  "topics": "regulation,children-education,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-15T20:00:00.000Z",
  "fetched_at": "2026-07-25T05:10:48.796Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/13009",
  "original_url": "https://arxiv.org/abs/2607.04763",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}