arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.04578cs.AIcs.MA
收藏

S-Agents:开放式环境中的自组织智能体

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

Fudan University(复旦大学);School of Data Science, Fudan University(复旦大学数据科学学院)

Jiaqi Chen, Yuxian Jiang, Jiachen Lu, Li Zhang

AI总结:

针对开放式环境中现有智能体协作依赖固定工作流、缺乏灵活组织结构的问题,受人类组织行为启发提出的S-Agents系统,通过智能体树、沙漏架构和非阻塞协作实现自主协调,在Minecraft环境的建造与资源收集任务中验证了有效性。

摘要:

借助大语言模型(LLMs),自主智能体已取得显著进步,具备了处理各类任务的能力。在开放式场景中,要优化协作的效率与效果,需要进行灵活调整。然而,当前研究主要侧重固定的、面向任务的工作流,却忽略了以智能体为中心的组织结构。受人类组织行为启发,我们提出了自组织智能体系统S-Agents,它包含用于动态工作流的“智能体树”结构、用于平衡信息优先级的“沙漏型智能体架构”,以及支持智能体间异步执行任务的“非阻塞协作”方法。该结构可自主协调一组智能体,无需人工干预就能高效应对开放动态环境的挑战。实验表明,S-Agents在Minecraft环境中能出色完成协作建造任务与资源收集,验证了其有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑