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

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Ng, Lynnette Hui Xian, Cruickshank, Iain J., Lim, Adrian Xuan Wei, Carley, Kathleen M.
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Multiagent Systems Computers and Society
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

_version_	1866909034983981056
author	Ng, Lynnette Hui Xian Cruickshank, Iain J. Lim, Adrian Xuan Wei Carley, Kathleen M.
author_facet	Ng, Lynnette Hui Xian Cruickshank, Iain J. Lim, Adrian Xuan Wei Carley, Kathleen M.
contents	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.
format	Preprint
id	arxiv_https___arxiv_org_abs_2605_07069
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems Ng, Lynnette Hui Xian Cruickshank, Iain J. Lim, Adrian Xuan Wei Carley, Kathleen M. Multiagent Systems Computers and Society 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.
title	Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems
topic	Multiagent Systems Computers and Society
url	https://arxiv.org/abs/2605.07069