OctoTools: 一个具有可扩展工具的代理框架,用于复杂推理
OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning
AI总结:
OctoTools通过标准化工具卡、规划器和执行器,提供一种无需训练的多代理框架,实现跨领域复杂推理,其在16种任务中达到9.3%的平均准确率提升。
摘要:
解决复杂推理任务可能涉及视觉理解、领域知识检索、数值计算和多步推理。现有方法通过外部工具增强大语言模型(LLMs),但受限于专用领域、有限工具类型或需要额外训练数据。本文介绍OctoTools,一种无需训练、用户友好且易于扩展的多代理框架,旨在处理跨领域的复杂推理。OctoTools引入标准化工具卡封装工具功能,一个用于高层和低层规划的规划器,以及一个执行器执行工具使用。我们验证了OctoTools在16种多样任务(包括MathVista、MMLU-Pro、MedQA和GAIA-Text)中的通用性,实现了相对于GPT-4o的9.3%的平均准确率提升。此外,OctoTools在给定相同工具集时,也比AutoGen、GPT-Functions和LangChain高出高达10.6%。通过全面分析、消融研究和在紧凑后端和嘈杂工具环境中的鲁棒性测试,OctoTools在任务规划、有效工具使用和多步问题解决方面表现出优势。代码、演示和可视化可在https://octotools.github.io/上公开获取。
英文摘要:
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/.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。