arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.06201cs.CL
收藏

EASYTOOL:通过简明的工具指令增强基于LLM的智能体

EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction

Fudan University(复旦大学);Microsoft Research Asia(微软亚洲研究院);Zhejiang University(浙江大学)

Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Yongliang Shen, Ren Kan, Dongsheng Li, Deqing Yang

AI总结:

提出EASYTOOL框架,将多样冗长的工具文档转化为统一简明的指令,显著降低token消耗并提升基于LLM的智能体在现实场景中的工具利用性能。

摘要:

为了处理复杂的现实世界任务,大型语言模型(LLMs)应用中的工具利用引起了越来越多的关注。要开发基于LLM的智能体,通常需要LLM从不同的工具文档中理解许多工具功能。但这些文档可能多种多样、冗余或不完整,这极大地影响了LLM使用工具的能力。为了解决这个问题,我们引入了EASYTOOL,这是一个将多样且冗长的工具文档转换为统一且简明的工具指令的框架,以便于工具使用。EasyTool从不同来源的广泛工具文档中提取关键信息,并详细阐述了统一接口(即工具指令),为基于LLM的智能体提供标准化的工具描述和功能。在多个不同任务上的大量实验表明,EasyTool能够显著减少token消耗,并提高现实场景中工具利用的性能。我们的代码将在未来于 https://github.com/microsoft/JARVIS/ 提供。

英文摘要:

To address intricate real-world tasks, there has been a rising interest in tool utilization in applications of large language models (LLMs). To develop LLM-based agents, it usually requires LLMs to understand many tool functions from different tool documentation. But these documentations could be diverse, redundant or incomplete, which immensely affects the capability of LLMs in using tools. To solve this, we introduce EASYTOOL, a framework transforming diverse and lengthy tool documentation into a unified and concise tool instruction for easier tool usage. EasyTool purifies essential information from extensive tool documentation of different sources, and elaborates a unified interface (i.e., tool instruction) to offer standardized tool descriptions and functionalities for LLM-based agents. Extensive experiments on multiple different tasks demonstrate that EasyTool can significantly reduce token consumption and improve the performance of tool utilization in real-world scenarios. Our code will be available at \url{https://github.com/microsoft/JARVIS/} in the future.

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。

↑