ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems
This provides a toolkit for developers building complex LLM-based multi-agent systems, but it is incremental as it builds on existing tools without new performance gains.
The authors tackled the lack of tools for recursive multi-agent systems where LLMs decide task delegation, by introducing ReDel, a toolkit with features like custom tool-use and debugging tools, resulting in an open-source package that helps identify improvements through visualization.
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.