ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems
Lists
Only you see this
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.
BibTeX
@inproceedings{zhu2024redel,
author = {Andrew Zhu and Liam Dugan and Chris Callison-Burch},
title = {{ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems}},
booktitle = {Conference on Empirical Methods in Natural Language Processing},
year = {2024},
url = {https://openreview.net/forum?id=BoBuI5x2l8},
}Loading related content...