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

TL;DR

This paper introduces S-Agents, a self-organizing multi-agent system inspired by human organizations, capable of autonomous collaboration and task execution in open-ended environments like Minecraft.

Contribution

It proposes a novel organizational structure and collaboration methods for autonomous agents, enabling dynamic, efficient teamwork without human oversight.

Findings

Successfully completed collaborative building tasks in Minecraft

Efficient resource collection demonstrated in experiments

Autonomous coordination without human intervention

Abstract

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.