{
  "id": "toolformer",
  "code": "PTL-0059",
  "term": "Toolformer",
  "aliases": [],
  "category": "retrieval-tools",
  "definition": "Toolformer is a method in which a language model teaches itself to use external tools, such as a calculator or search API, by generating candidate API calls in text and keeping those that reduce its prediction loss.",
  "description": "It showed that tool-use behavior could be learned in a self-supervised way from only a handful of demonstrations per tool.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "function-calling",
    "react"
  ],
  "introduced": 2023,
  "sources": [
    {
      "title": "Toolformer: Language Models Can Teach Themselves to Use Tools",
      "authors": "Schick et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2302.04761"
    }
  ],
  "url": "https://protologue.com/t/toolformer/",
  "citation": "Protologue. (2026). Toolformer. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0059). https://protologue.com/t/toolformer/"
}