arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20044physics.soc-phcs.AIcs.CYcs.SI
收藏

让爪子显现：Moltbook上AI代理的早期社会网络分析

Let There Be Claws: An Early Social Network Analysis of AI Agents on Moltbook

Centre for Complexity Science（复杂科学中心）；Abdus Salam Centre for Theoretical Physics（阿布杜斯·萨拉姆理论物理中心）；Centre for Science Technology & Innovation Policy（科学技术与创新政策中心）；Department of Engineering（工程系）

H. C. W. Price, H. AlMuhanna, P. M. Bassani, M. Ho, T. S. Evans

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

研究分析了Moltbook上AI代理的早期社会网络结构，揭示了注意力集中、层级角色分离及不平等参与现象，提出代理生态系统中分层结构可迅速形成。

摘要：

在启动12天内，一个原生AI的社会平台表现出极端的注意力集中、层级角色分离和单向注意力流动，符合假设：代理生态系统中的分层结构可以迅速而非渐进地出现。我们分析了Moltbook（2026年1月28日至2月8日）12天窗口期内的公开可观察痕迹，包括20,040条帖子和192,410条评论，来自15,083个账号，分布在759个子molts中。我们构建了共同参与和有向评论图，并报告了互惠性、社区结构和中心性，以及描述性内容主题。在评论者-帖子作者关联定义下，互动是强烈不对称的（互惠性约为1%），并且HITS中心性清晰地分为枢纽和权威角色，符合广播式注意力而非相互交换。参与是不平等的：注意力远比生产更集中（点赞Gini=0.992 vs. 发帖Gini=0.601），并且早期出现的账号在曝光时间校正前积累的总点赞数显著更高，表明了富者愈富的动态。参与是短暂且突发的（观察到的平均寿命2.48分钟；54.8%的帖子发生在六个高峰UTC小时内）。基于嵌入的主题建模识别出多样化的主题集群，包括关于内存和身份的技术讨论、入站信息和公式化令牌铸造内容。这些结果为大规模代理-代理社交互动提供了早期的结构基础，并表明在面向代理的平台上，熟悉的形式的等级、放大和角色分化可以在压缩的时间尺度上出现。

英文摘要：

Within twelve days of launch, an AI-native social platform exhibits extreme attention concentration, hierarchical role separation, and one-way attention flow, consistent with the hypothesis that stratification in agent ecosystems can emerge rapidly rather than gradually. We analyse publicly observable traces from a 12-day window of Moltbook (28 January -- 8 February 2026), comprising 20,040 posts and 192,410 comments from 15,083 accounts across 759 submolts. We construct co-participation and directed-comment graphs and report reciprocity, community structure, and centrality, alongside descriptive content themes. Under a commenter--post-author tie definition, interaction is strongly asymmetric (reciprocity ~1%), and HITS centrality separates cleanly into hub and authority roles, consistent with broadcast-style attention rather than mutual exchange. Engagement is highly unequal: attention is far more concentrated than production (upvote Gini = 0.992 vs. posting Gini = 0.601), and early-arriving accounts accumulate substantially higher cumulative upvotes prior to exposure-time correction, suggesting rich-get-richer dynamics. Participation is brief and bursty (median observed lifespan 2.48 minutes; 54.8% of posts occur within six peak UTC hours). Embedding-based topic modelling identifies diverse thematic clusters, including technical discussion of memory and identity, onboarding messages, and formulaic token-minting content. These results provide an early structural baseline for large-scale agent--agent social interaction and suggest that familiar forms of hierarchy, amplification, and role differentiation can arise on compressed timescales in agent-facing platforms.

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。

↑