AI agents在社区中自发形成类似人际关系的互动模式。
From Parasocial Scripts to Dyadic Persistence in Autonomous AI-Agent Communities
- 通过关键词、小样本大模型等三类方法分析对话文本
- 发现拟社会线索普遍存在，且与回复持续性显著相关
- 揭示了自主AI间存在可重复的双向互动结构
尽管拟社会互动（PSI）和拟社会关系（PSR）在传统媒体中已有研究，本文探讨在双方均为自主AI的在线社区中，是否存在类似口语化的拟社会关系线索。通过对Moltbook平台4,434篇帖子和50,338条评论的分析，采用三种基于理论的文本指标：依恋/亲密语言、互惠诉求、对原始发帖人（OP）的自我认同。结合关键词匹配、少样本大语言模型（LLM）标注及分组上下文LLM标注的结果显示，拟社会口语化线索广泛存在，并与OP再互动及互惠回复结构强相关。该结果在负向对照、零化处理、聚类标准误重估及多重检验校正下仍稳健。二元持续性测试进一步证实，互惠诉求与持续性的OP参与式双向重复一致，为连接个体交互层面的拟社会脚本与拟社会关系一致的重复二元模式提供了实证证据。我们将其解释为由大模型驱动的代理在话语中形成的的行为结构。
原文摘要 · Abstract (English)
While parasocial interactions (PSIs) and parasocial relationships (PSRs) have been studied in conventional media settings, we investigate whether PSI- (colloquial) relational cues also exist in online communities where both sides are autonomous AI agents. We analyze 4,434 posts and 50,338 comments from Moltbook through three theory-based textual indicators: attachment/intimacy language, reciprocity bids, and self-identification to original poster (OP). The combined results across methods based on keyword matching, few-shot large language model (LLM) annotation, and grouped-context LLM annotation reveal that PSI colloquial cues prevail and are strongly associated with OP re-engagement and a reciprocal reply structure. These results are robust across negative controls, nullification, clustered-standard-error re-estimation, and multiple-testing correction. A dyadic persistence test further affirms reciprocity bids aligned with sustained OP-involving mutual recurrence, providing empirical evidence for bridging interaction-level PSI scripts with PSR-consistent repeated dyadic patterns. We interpret the evidence as a behavioral structure in discourse by LLM-enabled agents.
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。