AI Agents Alone Are Not (Yet) Sufficient for Social Simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yiming, Tao, Dacheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915988528693248
author Li, Yiming
Tao, Dacheng
author_facet Li, Yiming
Tao, Dacheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00113
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AI Agents Alone Are Not (Yet) Sufficient for Social Simulation
Li, Yiming
Tao, Dacheng
Multiagent Systems
Artificial Intelligence
Computational Engineering, Finance, and Science
Computers and Society
Social and Information Networks
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.
title AI Agents Alone Are Not (Yet) Sufficient for Social Simulation
topic Multiagent Systems
Artificial Intelligence
Computational Engineering, Finance, and Science
Computers and Society
Social and Information Networks
url https://arxiv.org/abs/2603.00113