arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.06750cs.MAcs.AIcs.HCcs.LG
收藏

智能体能否自发形成社会?引入一种用于生成式多智能体以引发社会涌现的新颖架构

Can Agents Spontaneously Form a Society? Introducing a Novel Architecture for Generative Multi-Agents to Elicit Social Emergence

Kunming University of Science and Technology(昆明理工大学)

H. Zhang, J. Yin, M. Jiang, C. Su

AI总结:

本文提出生成式多智能体架构 ITCMA-S 及其支持社会交互的 LTRHA 框架,使智能体能够过滤有害行为并选择有利行动,沙盒实验表明智能体可自发形成具有内部等级的派系并组织集体活动。

摘要:

生成式智能体在特定任务中展现了出色的能力,但大多数框架集中于独立任务,缺乏对社会交互的关注。我们引入了一种名为 ITCMA-S 的生成式智能体架构,它包含个体智能体的基础框架以及一个支持多智能体间社会交互的名为 LTRHA 的框架。该架构使智能体能够识别并过滤掉对社会交互有害的行为,引导它们选择更有利的行动。我们设计了一个沙盒环境,以模拟多个无身份智能体间社会关系的自然演化来进行实验评估。结果表明,ITCMA-S 在多项评估指标上表现良好,展现了其主动探索环境、识别新智能体,以及通过持续行动和对话获取新信息的能力。观察显示,随着智能体彼此建立联系,它们会自发形成围绕选定领导者的具有内部等级的派系,并组织集体活动。

英文摘要:

Generative agents have demonstrated impressive capabilities in specific tasks, but most of these frameworks focus on independent tasks and lack attention to social interactions. We introduce a generative agent architecture called ITCMA-S, which includes a basic framework for individual agents and a framework called LTRHA that supports social interactions among multi-agents. This architecture enables agents to identify and filter out behaviors that are detrimental to social interactions, guiding them to choose more favorable actions. We designed a sandbox environment to simulate the natural evolution of social relationships among multiple identity-less agents for experimental evaluation. The results showed that ITCMA-S performed well on multiple evaluation indicators, demonstrating its ability to actively explore the environment, recognize new agents, and acquire new information through continuous actions and dialogue. Observations show that as agents establish connections with each other, they spontaneously form cliques with internal hierarchies around a selected leader and organize collective activities.

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。

↑