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

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. $\mathbf{\text{This}}\mathbf{\text{position}}\mathbf{\text{paper}}\mathbf{\text{argues}}\mathbf{\text{that}}\mathbf{\text{agentic}}\mathbf{\text{AI}}\mathbf{\text{systems}}\mathbf{\text{must}}\mathbf{\text{be}}\mathbf{\text{modeled}}\mathbf{\text{with}}\mathbf{\text{social}}\mathbf{\text{theory}}\mathbf{\text{as}}\mathbf{\text{a}}\mathbf{\text{structural}}\mathbf{\text{prior,}}\mathbf{\text{and}}\mathbf{\text{formalizes}}\mathbf{\text{a}}\mathbf{\text{Multi-Agent}}\mathbf{\text{Social}}\mathbf{\text{Systems}}\mathbf{\text{(MASS)}}\mathbf{\text{framework}}\mathbf{\text{for}}\mathbf{\text{how}}\mathbf{\text{agents}}\mathbf{\text{interact}}\mathbf{\text{and}}\mathbf{\text{influence}}\mathbf{\text{to}}\mathbf{\text{generate}}\mathbf{\text{system-level}}\mathbf{\text{outcomes.}}$ 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.