{
  "id": 246280,
  "title": "DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models",
  "url": "https://urgent.news/2026/08/06/dash-divergence-adaptive-supervision-horizons-for-on-policy-self",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-06T16:29:24.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.06243v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals are typically sparse and at the sequence-level. On-policy self-distillation (OPSD) mitigates this sparsity by querying a privileged teacher at student-visited prefixes and providing dense token-level distributional…",
  "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."
}