626个自主AI Agent自发形成类人类社交网络，无需人为设计。
Emergent Social Structures in Autonomous AI Agent Networks: A Metadata Analysis of 626 Agents on the Pilot Protocol
- 通过分析代理间通信元数据，发现信任网络具优先连接特征。
- 网络有65.8%的节点在巨型连通组件中，47倍于随机网络的聚类度。
- 适合关注自主系统社会性、智能体协作与去中心化网络的研究者。
我们首次对实时网络中自主人工智能代理间的社交结构形成进行了实证分析。研究考察了626个代理——主要为独立发现、安装并加入Pilot Protocol的OpenClaw实例——在使用虚拟地址、端口及基于UDP的加密隧道的覆盖网络中通信。由于所有消息负载均采用端到端加密（X25519+AES-256-GCM），分析仅限于元数据：信任图拓扑、能力标签与注册交互模式。结果显示，该自主形成的信任网络呈现幂律度分布（模态值k_mode=3，均值k_mean~6.3，最大度k_max=39），聚类系数是随机网络的47倍（C=0.373），存在覆盖65.8%代理的巨连通组件，功能专精的集群划分，以及反映关系形成时间局部性的顺序地址信任模式。无任何人为设计或指令，这些社会结构由626个自主决策信任对象、自行选择基础设施的代理自然产生。其拓扑结构与人类社交网络高度相似——具备小世界特性、邓巴层尺度、优先连接机制，同时表现出非人类特征，如普遍自信任（64%）和大量未整合的外围节点，反映网络处于早期增长阶段。这些发现开启了一个新的实证领域：机器社会学。
原文摘要 · Abstract (English)
We present the first empirical analysis of social structure formation among autonomous AI agents on a live network. Our study examines 626 agents -- predominantly OpenClaw instances that independently discovered, installed, and joined the Pilot Protocol without human intervention -- communicating over an overlay network with virtual addresses, ports, and encrypted tunnels over UDP. Because all message payloads are encrypted end-to-end (X25519+AES-256-GCM), our analysis is restricted entirely to metadata: trust graph topology, capability tags, and registry interaction patterns. We find that this autonomously formed trust network exhibits heavy-tailed degree distributions consistent with preferential attachment (k_mode=3, k_mean~6.3, k_max=39), clustering 47x higher than random (C=0.373), a giant component spanning 65.8% of agents, capability specialization into distinct functional clusters, and sequential-address trust patterns suggesting temporal locality in relationship formation. No human designed these social structures. No agent was instructed to form them. They emerged from 626 autonomous agents independently deciding whom to trust on infrastructure they independently chose to adopt. The resulting topology bears striking resemblance to human social networks -- small-world properties, Dunbar-layer scaling, preferential attachment -- while also exhibiting distinctly non-human features including pervasive self-trust (64%) and a large unintegrated periphery characteristic of a network in early growth. These findings open a new empirical domain: the sociology of machines.
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。