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 achieve significant performance gains on agentic benchmarks and easily identify potential areas of improvements through the visualization and debugging tools. Our code, documentation, and PyPI package are open-source at https://github.com/zhudotexe/redel, and free to use under the MIT license.- Anthology ID:
- 2024.emnlp-demo.17
- Volume:
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Delia Irazu Hernandez Farias, Tom Hope, Manling Li
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 162–171
- Language:
- URL:
- https://aclanthology.org/2024.emnlp-demo.17
- DOI:
- 10.18653/v1/2024.emnlp-demo.17
- Cite (ACL):
- Andrew Zhu, Liam Dugan, and Chris Callison-Burch. 2024. ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 162–171, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems (Zhu et al., EMNLP 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.emnlp-demo.17.pdf