EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction

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

Keywords: Tool Utilization, LLM-based Agent, Tool Documentation

TL;DR: We proposes EASYTOOL, a method that simplifies tool documentation into concise and structure tool instructions, improving tool utilization for LLM-based agents.

Abstract:

There has been a rising interest in utilizing tools in applications of autonomous agents based on large language models (LLMs) to address intricate real-world tasks.
To develop LLM-based agents, it usually requires LLMs to understand many tool functions from different tool documentations. However, 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 LLM-based agents on tool utilization in real-world scenarios.
Our code is available at https://github.com/microsoft/JARVIS/tree/main/easytool.

Submission Number: 7