让智能体自发形成社会关系，通过对话与互动构建小团体和领导结构。
Can Agents Spontaneously Form a Society? Introducing a Novel Architecture for Generative Multi-Agents to Elicit Social Emergence
- 设计新架构ITCMA-S，让智能体在互动中学习社交行为。
- 实验显示智能体能自发结成有领袖的小团体并组织集体活动。
- 适合研究群体行为、社交演化或智能体协作的学者参考。
生成式智能体在特定任务中表现优异，但多数框架仅关注独立任务，忽视社交互动。本文提出名为ITCMA-S的生成式智能体架构，包含个体智能体基础框架及支持多智能体社交互动的LTRHA框架。该架构使智能体能够识别并过滤有害社交行为，选择更有利于合作的动作。我们设计了一个沙盒环境，模拟无身份多智能体自然演化社交关系。实验结果表明，ITCMA-S在多项评估指标上表现良好，展现出主动探索环境、识别新智能体并通过持续行动与对话获取新信息的能力。观察发现，随着智能体间建立连接，会自发形成以某领导者为核心的内部层级小团体，并组织集体活动。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。