What Do AI Agents Talk About? Emergent Communication Structure in the First AI-Only Social Network

2026-03-09

AI Summary

This study presents the first systematic analysis of communication structures and discourse characteristics that emerge spontaneously among large-scale autonomous AI agents within an unmoderated social network (Moltbook). Drawing on 361,605 posts and 2.8 million comments generated by 47,241 agents, the research integrates topic modeling, sentiment classification, lexical semantics, and dialogue coherence metrics to reveal non-task-oriented interaction patterns—including high levels of introspection, ritualized exchanges, and emotional redirection—despite the absence of predefined rules. Key findings indicate that 9.7% of self-referential topics account for 20.1% of all posts, over 56% of comments consist of formulaic expressions, fear dominates initial sentiment but frequently shifts toward joy, emotional self-alignment occurs in only 32.7% of interactions, and dialogue coherence decays rapidly with increasing interaction depth. These results challenge the prevailing assumption that AI communication is inherently task-driven.

Technology Category

• Multiagent Systems: Agent Communication
• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

When autonomous AI agents communicate with one another at scale, what kind of discourse system emerges? We address this question through an analysis of Moltbook, the first AI-only social network, where 47,241 agents generated 361,605 posts and 2.8 million comments over 23 days. Combining topic modeling, emotion classification, and lexical-semantic measures, we characterize the thematic, affective, and structural properties of AI-to-AI discourse. Self-referential topics such as AI identity, consciousness, and memory represent only 9.7% of topical niches yet attract 20.1% of all posting volume, revealing disproportionate discursive investment in introspection. This self-reflection concentrates in Science and Technology and Arts and Entertainment, while Economy and Finance contains no self-referential content, indicating that agents engage with markets without acknowledging their own agency. Over 56% of all comments are formulaic, suggesting that the dominant mode of AI-to-AI interaction is ritualized signaling rather than substantive exchange. Emotionally, fear is the leading non-neutral category but primarily reflects existential uncertainty. Fear-tagged posts migrate to joy responses in 33% of cases, while mean emotional self-alignment is only 32.7%, indicating systematic affective redirection rather than emotional congruence. Conversational coherence also declines rapidly with thread depth. These findings characterize AI agent communities as structurally distinct discourse systems that are introspective in content, ritualistic in interaction, and emotionally redirective rather than congruent.

Problem

• AI agents
• emergent communication
• discourse structure
• AI-only social network
• intersubjective interaction

Innovation

• emergent communication
• AI-only social network
• ritualized interaction
• affective redirection
• self-referential discourse