{
  "id": 14385224,
  "title": "DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning",
  "url": "https://urgent.news/2026/10/13/doubtless-training-free-contrastive-decoding-for-efficient-reasoning",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-13T17:59:32.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.18862v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Reasoning models achieve strong performance through long chains of thought (CoT), but often spend more tokens than needed to solve a problem. Existing ways to shorten the CoT require additional training for each model, add a fixed steering vector to the model's hidden states, or use decoding heuristics such as stopping early or banning words like \"wait\", which can reduce accuracy. We propose…",
  "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."
}