Large Language Models as Tool Makers

by   Tianle Cai, et al.

Recent research shows the potential of enhancing the problem-solving ability of large language models (LLMs) through the use of external tools. However, prior work along this line depends on the availability of existing tools. In this work, we take an initial step towards removing this dependency by proposing a closed-loop framework, referred to as LLMs As Tool Makers (LATM), where LLMs create their own reusable tools for problem-solving. Our approach consists of two key phases: 1) tool making: an LLM acts as the tool maker that crafts tools for given tasks, where a tool is implemented as a Python utility function. 2) tool using: an LLM acts as the tool user, which applies the tool built by the tool maker for problem-solving. The tool user can be either the same or a different LLM from the tool maker. Tool-making enables an LLM to continually generate tools that can be applied to different requests so that future requests can call the corresponding APIs when beneficial for solving the tasks. Furthermore, the division of labor among LLMs for tool-making and tool-using phases introduces the opportunity to achieve cost effectiveness without degrading the quality of generated tools and problem solutions. For example, recognizing that tool-making demands more sophisticated capabilities than tool-using, we can apply a powerful yet resource-intensive model as the tool maker, and a lightweight while cost-effective model as the tool user. We validate the effectiveness of our approach across a variety of complex reasoning tasks, including Big-Bench tasks. With GPT-4 as the tool maker and GPT-3.5 as the tool user, LATM can achieve performance that is on par with using GPT-4 for both tool making and tool using, while the inference cost is significantly reduced.


page 4

page 6

page 14

page 17

page 18

page 19

page 20

page 21


Making Language Models Better Tool Learners with Execution Feedback

Tools serve as pivotal interfaces that enable humans to understand and r...

GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution

Augmenting large language models (LLM) to use external tools enhances th...

CREATOR: Disentangling Abstract and Concrete Reasonings of Large Language Models through Tool Creation

Large Language Models (LLMs) have demonstrated significant progress in u...

Tool Learning with Foundation Models

Humans possess an extraordinary ability to create and utilize tools, all...

SBT-instrumentation: A Tool for Configurable Instrumentation of LLVM Bitcode

The paper describes a member of the Symbiotic toolbox called sbt-instrum...

Insert-expansions for Tool-enabled Conversational Agents

This paper delves into an advanced implementation of Chain-of-Thought-Pr...

Experimenting with ChatGPT for Spreadsheet Formula Generation: Evidence of Risk in AI Generated Spreadsheets

Large Language Models (LLM) have become sophisticated enough that comple...

Please sign up or login with your details

Forgot password? Click here to reset