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

2026-07-04

AI Summary

This study addresses the decision-making distortions in existing LLM-based social simulations caused by reliance on manually crafted personas. To overcome this limitation, we propose a Survey-Driven Generative Agent-Based Modeling (GABM) framework that precisely maps empirical survey data onto LLM agents, establishing a closed loop between real-world evidence and behavioral experimentation. Using Germany’s fuel vehicle phase-out policy as a case study, the framework successfully simulates the dynamic evolution of public support. These findings validate the effectiveness of empirically grounded agents in complex social simulations and establish a robust methodological foundation and novel paradigm for reliable policy analysis driven by large language models.

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.

Problem

• Generative Agent-based Modeling
• Survey-grounded Personas
• LLM Simulation
• Mobility Policy Preference
• Behavioral Experiments

Innovation

• Survey-grounded GABM
• Generative Agent-based Modeling
• Empirically Grounded Personas
• LLM Agents
• Mobility Policy Preference