What Are Tools Anyway? A Survey from the Language Model Perspective

Zhiruo Wang, Zhoujun Cheng, Hao Zhu, Daniel Fried, Graham Neubig

Research Area: LMs with tools and code

Keywords: tool, agent, program

TL;DR: In this survey, we formally define what is a tool, when and how tools help, and existing issues with tool-related works.

Abstract: Language models (LMs) are powerful yet mostly for text generation tasks. Tools have substantially enhanced their performance for tasks that require complex skills. However, many works adopt the term “tool” in different ways, raising the question: What is a tool anyway? Subsequently, where and how do tools help LMs? In this survey, we provide a unified definition of tools as external programs used by LMs, and perform a systematic review of LM tooling scenarios and approaches. Grounded on this review, we empirically study the efficiency of various tooling methods by measuring their required compute and performance gains on various benchmarks, and highlight some challenges and potential future research in the field.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 162