{
  "id": 5485338,
  "title": "Rethinking On-Policy Distillation of Large Language Models II: One Training Example",
  "url": "https://urgent.news/2026/09/03/rethinking-on-policy-distillation-of-large-language-models-ii-one",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-03T17:54:38.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.04172v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. Existing work has mainly studied its algorithmic behavior, leaving the role of training data unclear. We examine this role at the data-minimal limit by training on a single query. One-shot OPD keeps improving for hundreds of steps and recovers most of full-data OPD's gain across…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}