{
  "id": 16554905,
  "title": "NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding",
  "url": "https://urgent.news/2026/10/23/ngramrl-accelerating-rl-post-training-for-structured-generation-via",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-23T16:47:29.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.32881v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Reinforcement learning (RL) post-training improves the reasoning capabilities of large language models, but its cost is dominated by autoregressive rollout generation, which can exceed 70% of training time. Existing speculative-decoding methods are poorly suited to this setting: model-based drafters consume scarce GPU memory and may become misaligned as the policy evolves, while existing…",
  "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."
}