{
  "id": "budget-forcing",
  "code": "PTL-0157",
  "term": "Budget Forcing",
  "aliases": [
    "s1",
    "wait token",
    "thinking budget control"
  ],
  "category": "test-time",
  "definition": "Budget forcing controls how long a reasoning model thinks at inference time, by forcibly ending its reasoning when a token budget is reached or by appending a word such as \"Wait\" when it tries to stop early, which makes it keep reasoning.",
  "description": "It was introduced with s1, a model fine-tuned on only about a thousand reasoning examples, where extending thinking with budget forcing improved accuracy on competition math. It is a simple way to trade compute for accuracy, though the gains flatten beyond a point.",
  "example": null,
  "broader": [
    "test-time-compute-scaling"
  ],
  "narrower": [],
  "related": [
    "reasoning-model",
    "extended-thinking",
    "overthinking"
  ],
  "introduced": 2025,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "s1: Simple test-time scaling",
      "authors": "Muennighoff et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2501.19393"
    }
  ],
  "url": "https://protologue.com/t/budget-forcing/",
  "citation": "Protologue. (2026). Budget Forcing. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0157). https://protologue.com/t/budget-forcing/"
}