OctoTools：一個具備可擴展工具的代理框架，用於複雜推理

OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning

February 16, 2025

作者: Pan Lu, Bowen Chen, Sheng Liu, Rahul Thapa, Joseph Boen, James Zou

cs.AI

摘要

解決複雜的推理任務可能涉及視覺理解、領域知識檢索、數值計算以及多步驟推理。現有方法通過外部工具增強大型語言模型（LLMs），但這些方法僅限於特定領域、工具類型有限或需要額外的訓練數據。本文介紹了OctoTools，這是一個無需訓練、用戶友好且易於擴展的開源代理框架，旨在應對跨多個領域的複雜推理任務。OctoTools引入了標準化的工具卡片來封裝工具功能，一個用於高層次和低層次規劃的規劃器，以及一個執行工具使用的執行器。我們在16個多樣化任務（包括MathVista、MMLU-Pro、MedQA和GAIA-Text）上驗證了OctoTools的通用性，平均準確率比GPT-4o提升了9.3%。此外，在提供相同工具集的情況下，OctoTools在AutoGen、GPT-Functions和LangChain上的表現提升了高達10.6%。通過全面的分析和消融實驗，OctoTools在任務規劃、有效工具使用以及多步驟問題解決方面展現了顯著優勢。

English

Solving complex reasoning tasks may involve visual understanding, domain knowledge retrieval, numerical calculation, and multi-step reasoning. Existing methods augment large language models (LLMs) with external tools but are restricted to specialized domains, limited tool types, or require additional training data. In this paper, we introduce OctoTools, a training-free, user-friendly, and easily extensible open-source agentic framework designed to tackle complex reasoning across diverse domains. OctoTools introduces standardized tool cards to encapsulate tool functionality, a planner for both high-level and low-level planning, and an executor to carry out tool usage. We validate OctoTools' generality across 16 diverse tasks (including MathVista, MMLU-Pro, MedQA, and GAIA-Text), achieving substantial average accuracy gains of 9.3% over GPT-4o. Furthermore, OctoTools outperforms AutoGen, GPT-Functions and LangChain by up to 10.6% when given the same set of tools. Through comprehensive analysis and ablations, OctoTools demonstrates advantages in task planning, effective tool usage, and multi-step problem solving.