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

arXiv: https://arxiv.org/abs/2605.07069 · HTML: https://mlsanity.com/paper/2605.07069/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 42 of its 104 references that are in the map.
- First posted on arXiv 8 May 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [Multi-Agent Reinforcement Learning is a Sequence Modeling Problem](https://mlsanity.com/paper/2205.14953/) (2022)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [LLM Generated Persona is a Promise with a Catch](https://mlsanity.com/paper/2503.16527/) (2025)
- [Online Human-Bot Interactions: Detection, Estimation, and Characterization](https://mlsanity.com/paper/1703.03107/) (2017)
- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents](https://mlsanity.com/paper/2402.12327/) (2024)
- [Large Language Models Miss the Multi-Agent Mark](https://mlsanity.com/paper/2505.21298/) (2025)
- [Examining Identity Drift in Conversations of LLM Agents](https://mlsanity.com/paper/2412.00804/) (2024)
- [Simulating Rumor Spreading in Social Networks using LLM Agents](https://mlsanity.com/paper/2502.01450/) (2025)
- [Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook](https://mlsanity.com/paper/2602.14299/) (2026)
- [Evolution of Social Norms in LLM Agents using Natural Language](https://mlsanity.com/paper/2409.00993/) (2024)
- [Understanding Incentives: Mechanism Design becomes Algorithm Design](https://mlsanity.com/paper/1305.4002/) (2013)
- [AI Agents and the Law](https://mlsanity.com/paper/2508.08544/) (2025)
- [Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation](https://mlsanity.com/paper/2604.18005/) (2026)

## Built on by (most cited first, 5 of 5)

- [Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models](https://mlsanity.com/paper/2607.27512/) (2026)
- [AgentSociety: Incentivizing Agentic Social Intelligence](https://mlsanity.com/paper/2605.26203/) (2026)
- [You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents](https://mlsanity.com/paper/2605.27586/) (2026)
- [Modeling Social Dynamics with an LLM-Enabled Agent Based Network-Dynamic (LAND) Model](https://mlsanity.com/paper/2608.00929/) (2026)
- [MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science](https://mlsanity.com/paper/2609.38392/) (2026)

## Abstract (arXiv)

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. 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.