Agent-based modeling and simulation has evolved as a powerful tool for modeling complex systems, offering insights into emergent behaviors and interactions among diverse agents. Integrating large language models into agent-based modeling and simulation presents a promising avenue for enhancing simulation capabilities. This paper surveys the landscape of utilizing large language models in agent-based modeling and simulation, examining their challenges and promising future directions. In this survey, since this is an interdisciplinary field, we first introduce the background of agent-based modeling and simulation and large language model-empowered agents. We then discuss the motivation for applying large language models to agent-based simulation and systematically analyze the challenges in environment perception, human alignment, action generation, and evaluation. Most importantly, we provide a comprehensive overview of the recent works of large language model-empowered agent-based modeling and simulation in multiple scenarios, which can be divided into four domains: cyber, physical, social, and hybrid, covering simulation of both real-world and virtual environments. Finally, since this area is new and quickly evolving, we discuss the open problems and promising future directions.

翻译：智能体建模与仿真已发展为建模复杂系统的强大工具，能够揭示不同智能体间的涌现行为与交互机制。将大语言模型整合至智能体建模与仿真中，为提升仿真能力提供了有前景的路径。本文系统梳理了在智能体建模与仿真中应用大语言模型的研究现状，审视其面临的挑战与未来发展方向。鉴于该领域的跨学科特性，我们首先介绍智能体建模与仿真及大语言模型赋能智能体的背景知识。继而从环境感知、人类对齐、动作生成与评估四个维度，系统分析将大语言模型应用于智能体仿真的动机与挑战。尤为重要的是，我们对近期大语言模型赋能智能体建模与仿真在多种场景下的研究工作进行了全面综述——这些场景可划分为四大领域：网络域、物理域、社会域与混合域，涵盖真实环境与虚拟环境的仿真。最后，鉴于该新兴领域的快速演进特性，我们探讨了当前存在的开放性问题与未来值得探索的方向。