{
  "id": 6088834,
  "title": "RISE: Recursive Improvement via Self-Extrapolating Policy Distillation",
  "url": "https://urgent.news/2026/09/04/rise-recursive-improvement-via-self-extrapolating-policy-distillation",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-04T15:47:51.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.05295v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suffer from distribution mismatch, while self-distillation with privileged conditioning is limited by in-context learning capacity. We propose \\textbf{RISE} (\\textbf{R}ecursive \\textbf{I}mprovement via…",
  "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."
}