A Taxonomy for Autonomous LLM-Powered Multi-Agent Architectures

Thorsten Händler

2023

Abstract

Large language models (LLMs) have revolutionized the field of artificial intelligence, endowing it with sophisticated language understanding and generation capabilities. However, when faced with more complex and interconnected tasks that demand a profound and iterative thought process, LLMs reveal their inherent limitations. Autonomous LLM-powered multi-agent systems represent a strategic response to these challenges. While these architectures hold promising potential in amplifying AI capabilities, striking the right balance between different levels of autonomy and alignment remains the crucial challenge for their effective operation. This paper proposes a comprehensive multi-dimensional taxonomy, engineered to analyze how autonomous LLM-powered multi-agent systems balance the dynamic interplay between autonomy and alignment across various aspects inherent to architectural viewpoints such as goal-driven task management, agent composition, multi-agent collaboration, and context interaction. Our taxonomy aims to empower researchers, engineers, and AI practitioners to systematically analyze the architectural dynamics and balancing strategies employed by these increasingly prevalent AI systems. The exploratory taxonomic classification of selected representative LLM-powered multi-agent systems illustrates its practical utility and reveals potential for future research and development. An extended version of this paper is available on arXiv (Händler, 2023).

Paper Citation

in Harvard Style

Händler T. (2023). A Taxonomy for Autonomous LLM-Powered Multi-Agent Architectures. In Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 3: KMIS; ISBN 978-989-758-671-2, SciTePress, pages 85-98. DOI: 10.5220/0012239100003598

in Bibtex Style

@conference{kmis23,
author={Thorsten Händler},
title={A Taxonomy for Autonomous LLM-Powered Multi-Agent Architectures},
booktitle={Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 3: KMIS},
year={2023},
pages={85-98},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012239100003598},
isbn={978-989-758-671-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 3: KMIS
TI - A Taxonomy for Autonomous LLM-Powered Multi-Agent Architectures
SN - 978-989-758-671-2
AU - Händler T.
PY - 2023
SP - 85
EP - 98
DO - 10.5220/0012239100003598
PB - SciTePress