ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912105195634688 |
|---|---|
| author | Zhu, Andrew Dugan, Liam Callison-Burch, Chris |
| author_facet | Zhu, Andrew Dugan, Liam Callison-Burch, Chris |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02248 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems Zhu, Andrew Dugan, Liam Callison-Burch, Chris Computation and Language Multiagent Systems Software Engineering I.2.7 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. |
| title | ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems |
| topic | Computation and Language Multiagent Systems Software Engineering I.2.7 |
| url | https://arxiv.org/abs/2408.02248 |