ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems

TL;DR

ReDel is an open-source toolkit designed to facilitate the creation and debugging of recursive multi-agent systems powered by Large Language Models, supporting custom tools, delegation, and interactive visualization.

Contribution

It introduces ReDel, the first toolkit supporting recursive multi-agent systems with flexible delegation, tool-use, and debugging features, enhancing development and analysis capabilities.

Findings

Enables easy visualization and debugging of multi-agent interactions.

Supports custom tool integration and flexible delegation schemes.

Provides an interactive web interface for system management.

Abstract

Recently, there has been increasing interest in using Large Language Models (LLMs) to construct complex multi-agent systems to perform tasks such as compiling literature reviews, drafting consumer reports, and planning vacations. Many tools and libraries exist for helping create such systems, however none support recursive multi-agent systems -- where the models themselves flexibly decide when to delegate tasks and how to organize their delegation structure. In this work, we introduce ReDel: a toolkit for recursive multi-agent systems that supports custom tool-use, delegation schemes, event-based logging, and interactive replay in an easy-to-use web interface. We show that, using ReDel, we are able to easily identify potential areas of improvements through the visualization and debugging tools. Our code, documentation, and PyPI package are open-source and free to use under the MIT license at https://github.com/zhudotexe/redel.