AI 中文总结
本研究提出基于调查的生成式智能体建模框架，将德国514名调查受访者转化为LLM智能体，模拟公众对淘汰新型内燃机汽车的政策偏好动态，以助力行为实验。
AI 中文摘要
大语言模型（LLM）已越来越多地被用于模拟社会复杂且由交互驱动的任务。然而，大多数现有研究依赖于人工构建的画像。由于画像设计强烈影响智能体解释情境和做出决策的方式，开发基于实证的智能体轮廓是这一未充分探索研究领域的重要方面。为解决这一局限，我们提出了基于调查的生成式智能体建模（GABM）模拟框架，该框架将真实调查受访者转化为生成式LLM智能体。我们框架的主要目标是展示精心设计的画像如何能够实现使用LLM进行决策的逼真模拟，以助力行为实验。我们通过德国流动性政策偏好动态的案例研究来说明该框架的适用性，重点关注公众对逐步淘汰新型内燃机汽车的支持，这是欧盟净零目标的一部分。我们的基准基于514名调查受访者，每位受访者被转化为自然语言画像，其依据是人口统计学特征、政治倾向、出行行为、燃料使用经验以及与气候相关的态度。模拟目标是检验支持度如何随时间演变、智能体如何在多轮中转变立场，以及在不断变化的社会和政策情境下，基于调查的不同画像的反应存在何种差异。
英文摘要
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.
