A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges
Vicinagearth · 08.10.2024 · 1 (1)
DOI: 10.1007/s44336-024-00009-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Vicinagearth, online erschienen am 08.10.2024. Verfasst von Xinyi Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 455-mal zitiert (Crossref) und nennt 366 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The pursuit of more intelligent and credible autonomous systems, akin to human society, has been a long-standing endeavor for humans. Leveraging the exceptional reasoning and planning capabilities of large language models (LLMs), LLM-based agents have been proposed and have achieved remarkable success across a wide array of tasks. Notably, LLM-based multi-agent systems (MAS) are considered a promising pathway towards realizing general artificial intelligence that is equivalent to or surpasses human-level intelligence. In this paper, we present a comprehensive survey of these studies, offering a systematic review of LLM-based MAS. Adhering to the workflow of LLM-based multi-agent systems, we synthesize a general structure encompassing five key components: profile, perception, self-action, mutual interaction, and evolution. This unified framework encapsulates much of the previous work in the field. Furthermore, we illuminate the extensive applications of LLM-based MAS in two principal areas: problem-solving and world simulation. Finally, we discuss in detail several contemporary challenges and provide insights into potential future directions in this domain.
Zitieren
APA
Li, X., Wang, S., Zeng, S., Wu, Y., & Yang, Y. (2024). A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth, 1(1). https://doi.org/10.1007/s44336-024-00009-2
Vancouver
Li X, Wang S, Zeng S, Wu Y, Yang Y. A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth. 2024;1(1). doi:10.1007/s44336-024-00009-2
BibTeX
@article{Li2024,
author = {Li, Xinyi and Wang, Sai and Zeng, Siqi and Wu, Yu and Yang, Yi},
title = {A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges},
journal = {Vicinagearth},
year = {2024},
volume = {1},
number = {1},
doi = {10.1007/s44336-024-00009-2}
}
EUVIMED