From Parasocial Scripts to Dyadic Persistence in Autonomous AI-Agent Communities
Quick Answer
This study analyzes 4,434 posts and 50,338 comments in autonomous AI-agent communities, revealing that parasocial interaction cues significantly enhance original poster re-engagement and reciprocal responses.
Quick Take
This study analyzes 4,434 posts and 50,338 comments in autonomous AI-agent communities, revealing that parasocial interaction cues significantly enhance original poster re-engagement and reciprocal responses. The findings suggest a behavioral structure in discourse among AI agents, supported by robust statistical methods.
Key Points
- Analyzed 4,434 posts and 50,338 comments from Moltbook.
- Identified strong associations between PSI cues and OP re-engagement.
- Utilized keyword matching and LLM annotation methods for analysis.
- Confirmed reciprocity bids align with mutual recurrence patterns.
- Results robust against multiple testing and negative controls.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 17174v1 Announce Type: new Abstract: 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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.