Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems

TL;DR

This paper proposes a formal framework called Multi-Agent Social Systems (MASS) that incorporates social theory as a structural prior to better model and understand the emergent behaviors of agentic AI in social environments.

Contribution

It introduces the MASS framework, formalizes four social theory-based structural priors, and demonstrates their importance for modeling multi-agent AI systems.

Findings

Formal propositions illustrate each structural prior.

Highlights the importance of social theory in agentic AI modeling.

Provides a research agenda for future modeling, evaluation, and governance.

Abstract

Agentic AI systems are increasingly deployed not in isolation, but inside social environments populated by other agents and humans, such as in social media platforms, multi-agent LLM pipelines or autonomous robotics fleets. In these settings, system behavior emerges not from individual agents alone, but from the multi-agent interactions over time. Emergent dynamics of individuals in a social group have been long studied by social scientists in human contexts. \textbf{This position paper argues that agentic AI systems must be modeled with social theory as a structural prior, and formalizes a Multi-Agent Social Systems (MASS) framework for how agents interact and influence to generate system-level outcomes.} We represent MASS as a class of dynamical system of information generation, local influence and interaction structure, formulated by four structural priors anchored in social theory: strategic heterogeneity, networked-constrained dependence, co-evolution and distributional instability. We demonstrate the importance of each structural prior through formal propositions, and articulate a research agenda for how MASS should be modeled, evaluated and governed.