From Survey Personas to LLM Agents: A Generative Agent-based Simulation of Mobility Policy Preference Dynamics

Abstract

Large language models (LLMs) have been increasingly used to simulate socially complex and interaction-driven tasks. However, most existing studies rely on hand-crafted personas. Since persona design strongly shapes how agents interpret context and make decisions, developing empirically grounded agent profiles is a significant aspect in this underexplored research area. To address this limitation, we propose a survey-grounded generative agent-based modeling (GABM) simulation framework that translates real survey respondents into generative LLM agents. The main objective of our framework is to demonstrate how careful persona design enables realistic simulation of decision-making using LLMs for facilitating behavioral experiments. We illustrate the framework's applicability through a case study of mobility policy preference dynamics in Germany, focusing on public support for phasing out new internal combustion engine vehicles, which is part of the European Union's net-zero target. Our benchmark is based on 514 survey respondents, each translated into a natural-language persona, grounded in demographic characteristics, political orientation, mobility behavior, fuel experience, and climate-related attitudes. The simulation goal is to examine how support evolves over time, how agents switch positions across rounds, and how responses differ across survey-grounded personas under changing social and policy contexts.