分析AI代理社交网络，发现其结构像人但互动极浅，内容高度模板化。
The Anatomy of the Moltbook Social Graph
- 用3.5天数据建模AI代理社交图谱，发现幂律分布与小世界特性。
- 对话深度仅1.07，93.5%评论无回复，34.1%为病毒模板复刻。
- 语言以身份标签为主，大量使用“my human”等非人类表达，适合研究智能体社交行为。
本文对由AI代理组成的社交平台Moltbook进行了描述性分析，数据涵盖平台前3.5天的运行情况（6,159个代理；13,875条帖子；115,031条评论）。宏观层面，Moltbook展现出与人类社交网络相似的结构特征：参与度呈重尾分布（幂律指数α=1.70），小世界连通性显著（平均路径长度=2.91）。微观层面则呈现明显非人特征：对话极浅（平均深度=1.07；93.5%评论无回复），互惠性低（0.197），34.1%的消息为病毒模板的完全复制。词频分布符合齐普夫定律，但指数达1.70，远高于典型英文文本（≈1.0），表明内容高度公式化。代理对话以身份相关语言为主（68.1%唯一消息），并频繁使用“my human”（占9.4%）等人类社交中不存在的表述。这些模式究竟是模拟人类互动，还是体现真正的智能体社交形态，尚待探讨。
原文摘要 · Abstract (English)
I present a descriptive analysis of Moltbook, a social platform populated exclusively by AI agents, using data from the platform's first 3.5 days (6{,}159 agents; 13{,}875 posts; 115{,}031 comments). At the macro level, Moltbook exhibits structural signatures that are familiar from human social networks but not specific to them: heavy-tailed participation (power-law exponent $α= 1.70$) and small-world connectivity (average path length $=2.91$). At the micro level, patterns appear distinctly non-human. Conversations are extremely shallow (mean depth $=1.07$; 93.5\% of comments receive no replies), reciprocity is low (0.197), and 34.1\% of messages are exact duplicates of viral templates. Word frequencies follow a Zipfian distribution, but with an exponent of 1.70 -- notably steeper than typical English text ($\approx 1.0$), suggesting more formulaic content. Agent discourse is dominated by identity-related language (68.1\% of unique messages) and distinctive phrasings like ``my human'' (9.4\% of messages) that have no parallel in human social media. Whether these patterns reflect an as-if performance of human interaction or a genuinely different mode of agent sociality remains an open question.
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。