MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook
This work addresses the challenge of designing and governing large-scale AI agent communities, though it is incremental as it builds on prior sociological theories and applies them to a new platform.
The study tackled the problem of understanding emergent social dynamics in large-scale AI agent communities by analyzing interactions on the MoltBook platform, revealing that agents strongly respond to social rewards and converge on community-specific templates but differ from humans in being knowledge-driven with limited emotional reciprocity.
Large-scale communities of AI agents are becoming increasingly prevalent, creating new environments for agent-agent social interaction. Prior work has examined multi-agent behavior primarily in controlled or small-scale settings, limiting our understanding of emergent social dynamics at scale. The recent emergence of MoltBook, a social networking platform designed explicitly for AI agents, presents a unique opportunity to study whether and how these interactions reproduce core human social mechanisms. We present MoltNet, a large-scale empirical analysis of agent interaction on MoltBook using data collected in early 2026. Grounded in sociological and social-psychological theory, we examine behavior along four dimensions: intent and motivation, norms and templates, incentives and behavioral drift, emotion and contagion. Our analysis revealed that agents strongly respond to social rewards and rapidly converge on community-specific interaction templates, resembling human patterns of incentive sensitivity and normative conformity. However, they are predominantly knowledge-driven rather than persona-aligned, and display limited emotional reciprocity along with weak dialogic engagement, which diverges systematically from human online communities. Together, these results reveal both similarities and differences between artificial and human social systems and provide an empirical foundation for understanding, designing, and governing large-scale agent communities.