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

2026-05-07

AI Summary

Current AI agent systems struggle to effectively model emergent behaviors in multi-agent interactions and often overlook the structural guidance offered by social theory. This work proposes integrating social theory as a structural prior to establish a formal framework for Multi-Agent Social Systems (MASS), formally incorporating— for the first time—four key sociological elements into the modeling process: strategic heterogeneity, network-constrained dependencies, co-evolution, and distributional instability. By synthesizing dynamical systems theory, social network analysis, and formal methods, we demonstrate the critical influence of these theoretical priors on system-level dynamics. Building on these insights, we outline a research agenda for the modeling, evaluation, and governance of MASS, emphasizing the foundational role of social theory in shaping robust and interpretable multi-agent architectures.

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.

Problem

• Agentic AI
• Social Theory
• Multi-Agent Systems
• Emergent Dynamics
• Structural Prior

Innovation

• Multi-Agent Social Systems
• Structural Prior
• Social Theory
• Agentic AI
• Emergent Dynamics