AI Agents Alone Are Not (Yet) Sufficient for Social Simulation
For researchers in AI and social simulation, this paper highlights critical limitations of using LLM agents for faithful human behavior modeling, advocating for more rigorous frameworks.
This position paper argues that current LLM-based agents are insufficient for social simulation due to a mismatch between agent optimization (role-playing plausibility) and simulation requirements (behavioral validity, environmental dynamics, protocol sensitivity). It proposes a unified Markov game formulation to guide design, evaluation, and interpretation.
Recent advances in large language models (LLMs) have spurred growing interest in using LLM-integrated agents for social simulation, often under the implicit assumption that realistic population dynamics will emerge once role-specified agents are placed in a networked multi-agent setting. This position paper argues that LLM-based agents alone are not (yet) sufficient for social simulation. We attribute this over-optimism to a systematic mismatch between what current agent pipelines are typically optimized and validated to produce and what simulation-as-science requires. Concretely, role-playing plausibility does not imply faithful human behavioral validity; collective outcomes are frequently mediated by agent-environment co-dynamics rather than agent-agent messaging alone; and results can be dominated by interaction protocols, scheduling, and initial information priors. To make these underlying mechanisms explicit and auditable, we propose a unified formulation of AI agent-based social simulation as an environment-involved Markov game with explicit exposure and scheduling mechanisms, from which we derive concrete actions for design, evaluation, and interpretation.