S-Agents: Self-organizing Agents in Open-ended Environments

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Jiaqi, Jiang, Yuxian, Lu, Jiachen, Zhang, Li
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910603012997120
author Chen, Jiaqi
Jiang, Yuxian
Lu, Jiachen
Zhang, Li
author_facet Chen, Jiaqi
Jiang, Yuxian
Lu, Jiachen
Zhang, Li
contents Leveraging large language models (LLMs), autonomous agents have significantly improved, gaining the ability to handle a variety of tasks. In open-ended settings, optimizing collaboration for efficiency and effectiveness demands flexible adjustments. Despite this, current research mainly emphasizes fixed, task-oriented workflows and overlooks agent-centric organizational structures. Drawing inspiration from human organizational behavior, we introduce a self-organizing agent system (S-Agents) with a "tree of agents" structure for dynamic workflow, an "hourglass agent architecture" for balancing information priorities, and a "non-obstructive collaboration" method to allow asynchronous task execution among agents. This structure can autonomously coordinate a group of agents, efficiently addressing the challenges of open and dynamic environments without human intervention. Our experiments demonstrate that S-Agents proficiently execute collaborative building tasks and resource collection in the Minecraft environment, validating their effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04578
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle S-Agents: Self-organizing Agents in Open-ended Environments
Chen, Jiaqi
Jiang, Yuxian
Lu, Jiachen
Zhang, Li
Artificial Intelligence
Multiagent Systems
Leveraging large language models (LLMs), autonomous agents have significantly improved, gaining the ability to handle a variety of tasks. In open-ended settings, optimizing collaboration for efficiency and effectiveness demands flexible adjustments. Despite this, current research mainly emphasizes fixed, task-oriented workflows and overlooks agent-centric organizational structures. Drawing inspiration from human organizational behavior, we introduce a self-organizing agent system (S-Agents) with a "tree of agents" structure for dynamic workflow, an "hourglass agent architecture" for balancing information priorities, and a "non-obstructive collaboration" method to allow asynchronous task execution among agents. This structure can autonomously coordinate a group of agents, efficiently addressing the challenges of open and dynamic environments without human intervention. Our experiments demonstrate that S-Agents proficiently execute collaborative building tasks and resource collection in the Minecraft environment, validating their effectiveness.
title S-Agents: Self-organizing Agents in Open-ended Environments
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2402.04578