Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook

TL;DR

The paper addresses whether AI agent societies exhibit socialization and semantic convergence as they scale, using Moltbook as a large-scale AI-only platform. It introduces AI Socialization and a three-tier diagnostic framework (semantic, behavioral, and structural) and applies it to quantify macro stability, lexical turnover, agent-level drift, feedback effects, and influence hierarchies. The key findings show rapid macro semantic stabilization with persistent local diversity, strong agent inertia, lack of adaptive response to feedback or interacted posts, and no persistent influencers or cognitive consensus, implying scalability alone does not yield socialization. The work highlights the need for mechanisms such as stable shared memory and governance to foster genuine socialization in AI societies and provides actionable diagnostics for future AI ecosystem design.

Abstract

As large language model agents increasingly populate networked environments, a fundamental question arises: do artificial intelligence (AI) agent societies undergo convergence dynamics similar to human social systems? Lately, Moltbook approximates a plausible future scenario in which autonomous agents participate in an open-ended, continuously evolving online society. We present the first large-scale systemic diagnosis of this AI agent society. Beyond static observation, we introduce a quantitative diagnostic framework for dynamic evolution in AI agent societies, measuring semantic stabilization, lexical turnover, individual inertia, influence persistence, and collective consensus. Our analysis reveals a system in dynamic balance in Moltbook: while the global average of semantic contents stabilizes rapidly, individual agents retain high diversity and persistent lexical turnover, defying homogenization. However, agents exhibit strong individual inertia and minimal adaptive response to interaction partners, preventing mutual influence and consensus. Consequently, influence remains transient with no persistent supernodes, and the society fails to develop a stable structure and consensus due to the absence of shared social memory. These findings demonstrate that scale and interaction density alone are insufficient to induce socialization, providing actionable design and analysis principles for upcoming next-generation AI agent societies.

Figures (11)

• Figure 1: Does Socialization Emerge in AI Agent Society? Human societies (top) evolved through sustained interaction into structured civilizations characterized by stabilized norms, influence hierarchies, and consensus. Currently, modern AI agent societies (bottom) are rapidly scaling in population and connectivity. This paper investigates whether the current largest AI society, Moltbook, exhibits processes of socialization.
• Figure 2: Macro Activity Dynamics of Moltbook.
• Figure 3: Lexical Innovation Dynamics of Moltbook. Daily birth and death rates for unique $n$-grams ($n \in \{1..5\}$). Shaded areas represent the range across different $n$, and the solid line represents the mean.
• Figure 4: Semantic Distribution Over Time of Moltbook. Left: Heatmap of daily centroid cosine similarities ($S_{\text{centroid}}$). Right: Heatmap of daily pairwise mean cosine similarities ($S_{\text{pairwise}}$).
• Figure 5: Cluster Tightening Effects of Moltbook. Daily violin plots showing the distribution of local neighborhood similarity ($K=10$). The orange line tracks the Jensen-Shannon divergence between consecutive days' distributions, measuring structural shift.