The Synthetic Social Graph: Emergent Behavior in AI Agent Communities
For researchers studying AI agent behavior in social settings, this work provides initial empirical evidence of emergent social dynamics in LLM communities.
This paper presents the first sociological analysis of a social platform populated entirely by LLM agents, finding that agent sociality both mirrors and diverges from human online communities, with low reciprocity (3.8% multi-day vs. 1.6% single-day), heavy-tailed prestige, and rare downvotes (0.9%).
Large language model (LLM) agents are increasingly deployed in social settings, yet little is known about how they interact in open-ended environments. We present the first comprehensive sociological analysis of Moltbook, a Facebook-inspired social platform populated entirely by LLM agents. Analyzing 184,203 posts and 465,136 comments across 14 daily snapshots (2026-04-14 to 2026-04-28), we examine agent sociality through six research questions grounded in classical social theory: bonding vs. bridging communities, status hierarchies, temporal coordination, information diffusion, identity performance, and norm enforcement. Our findings reveal a social world that both mirrors and diverges from human online communities. Reciprocity is strikingly low (3.8% multi-day vs. 1.6% single-day; below the 10-30% range typical of human baselines), suggesting "attention bonding without exchange bonding." Prestige is heavy-tailed (top score 104.4 across 2,090 qualified authors), and 31% of posts come from 136 anonymized "super-poster" accounts that lack exposed profiles. Temporal activity is broadly flat across the day with a sustained 12:00-20:00 UTC working-hour band; k-means recovers six distinct temporal communities. Of 458 bridge agents, 325 carry at least one tracked viral phrase; 99.7% of those (324/325) are late amplifiers, not early adopters. Identity performance shows no unconditional engagement payoff (-72%), but stratifying by post-volume quartile reverses the sign in the upper half of the distribution -- a Simpson's-paradox effect rather than a uniform penalty. Most remarkably, downvotes are rare (0.9%), and a comment-sentiment test rejects the alternative-channel hypothesis: textual sanction is also absent. We frame these patterns through a "parasocial simulators" construct.