Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents256Conference: Proceedings of the ACM Web Conference 2025; April 28-May 2, 2025; Sydney, NSW, AustraliaProceedings of the ACM Web Conference 2025 (WWW ’25), April 28-May 2, 2025, Sydney, NSW, AustraliaDOI: 10.1145/3696410.3714825ISBN: 979-8-4007-1274-6/25/04CCS: Information systems Data mining
Zhengliang Shi Affiliation: Shandong University , Qingdao , China email: , Shen Gao Affiliation: University of Electronic Science and Technology of China , Chengdu , China email: , Lingyong Yan Affiliation: Baidu Inc. , Beijing , China email: , Yue Feng Affiliation: University of Birmingham , Birmingham , United kingdom email: , Xiuyi Chen Affiliation: Baidu Inc. , Beijing , China email: , Zhumin Chen Affiliation: Shandong University , Qingdap , China email: , Dawei Yin Affiliation: Baidu Inc. , Beijing , China email: , Suzan Verberne Affiliation: Leiden University , Leiden , Netherland email: and Zhaochun Ren Affiliation: Leiden University , Leiden , Netherland Note: Corresponding author. email:
Abstract
Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extend their utility, enabling them to solve practical tasks. Previous methods manually parse tool documentation and create in-context demonstrations, transforming tools into structured formats for LLMs to use in their step-by-step reasoning. However, this manual process requires domain expertise and struggles to scale to large toolsets. Additionally, these methods rely heavily on ad-hoc inference techniques or special tokens to integrate free-form LLM generation with tool-calling actions, limiting the LLM’s flexibility in handling diverse tool specifications and integrating multiple tools.
原文 arXiv:2405.16533;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2405.16533v2