Toolformer: Language Models Can Teach Themselves to Use Tools

Authors: Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, Thomas Scialom (2023)

arXiv: 2302.04761

Domains

Applications

TLDR (English)

Makes model generate "API-calling tokens" itself and evaluate usefulness through self-supervision. Foundational paper for function-calling/tool-use training paradigm, directly influencing GPT-4 function calling design.

TLDR（中文）

让模型自己生成"调用 API 的 token"并通过自监督评估有用性。是 function-calling / tool-use 训练范式的奠基论文，直接影响 GPT-4 function calling 的设计。

Appears in These Articles

• Agent 与工具使用：模型不只是聊天
• Agents and Tool Use: Models Are More Than Chat

Co-cited Papers

These papers appear in the same articles as this one

• Model Context Protocol (MCP) Anthropic (2024)
• Reflexion: Language Agents with Verbal Reinforcement Learning Noah Shinn et al. (2023)
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering John Yang et al. (2024)
• ReAct: Synergizing Reasoning and Acting in Language Models Shunyu Yao et al. (2022)

Related Papers

Other papers in the same domain

• Model Context Protocol (MCP) Anthropic (2024)
  Applications
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues? Carlos E. Jimenez et al. (2024)
  EvaluationApplications
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering John Yang et al. (2024)
  Applications
• Reflexion: Language Agents with Verbal Reinforcement Learning Noah Shinn et al. (2023)
  Applications
• Efficient Guided Generation for Large Language Models Brandon T. Willard et al. (2023)
  InferenceApplications
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models Shunyu Yao et al. (2023)
  ReasoningApplications