无需训练的多智能体框架，让大模型高效解决跨领域复杂推理问题。
OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning
- 用标准化工具卡封装功能，支持灵活扩展和用户自定义。
- 在16个任务上平均比GPT-4o高9.3%，最高超越其他框架10.6%。
- 适合需要多步推理与工具协作的科研、工程及教育场景。
解决复杂推理任务通常需要视觉理解、领域知识检索、数值计算和多步推理。现有方法虽通过外部工具增强大语言模型（LLMs），但受限于特定领域、工具类型有限或需额外训练数据。本文提出OctoTools，一个免训练、易用且可扩展的多智能体框架，用于跨领域复杂推理。OctoTools引入标准化工具卡封装工具功能，配备高低层规划器与执行器以实现工具调用。我们在16个多样化任务（包括MathVista、MMLU-Pro、MedQA和GAIA-Text）上验证其通用性，平均准确率相比GPT-4o提升9.3%。在相同工具集下，性能优于AutoGen、GPT-Functions和LangChain，最高提升达10.6%。通过全面分析、消融实验和鲁棒性测试，证明其在任务规划、工具有效使用及多步求解方面具备优势。代码、演示与可视化已公开于https://octotools.github.io/。
原文摘要 · Abstract (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 multi-agent 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 also outperforms AutoGen, GPT-Functions, and LangChain by up to 10.6% when given the same set of tools. Through comprehensive analysi, ablations, and robustness tests with compact backbones and noisy tool environments, OctoTools demonstrates advantages in task planning, effective tool usage, and multi-step problem solving. Code, demos, and visualization are publicly available at https://octotools.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。