Multi-Agent System (MAS) developing frameworks serve as the foundational infrastructure for social simulations powered by Large Language Models (LLMs). However, existing frameworks fail to adequately support large-scale simulation development due to inherent limitations in adaptability, configurability, reliability, and code reusability. For example, they cannot simulate a society where the agent population and profiles change over time. To fill this gap, we propose Agent-Kernel, a framework built upon a novel society-centric modular microkernel architecture. It decouples core system functions from simulation logic and separates cognitive processes from physical environments and action execution. Consequently, Agent-Kernel achieves superior adaptability, configurability, reliability, and reusability. We validate the framework's superiority through two distinct applications: a simulation of the Universe 25 (Mouse Utopia) experiment, which demonstrates the handling of rapid population dynamics from birth to death; and a large-scale simulation of the Zhejiang University Campus Life, successfully coordinating 10,000 heterogeneous agents, including students and faculty.
@article{arxiv.2512.01610,
title = {Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs},
author = {Yuren Mao and Peigen Liu and Xinjian Wang and Rui Ding and Jing Miao and Hui Zou and Mingjie Qi and Wanxiang Luo and Longbin Lai and Kai Wang and Zhengping Qian and Peilun Yang and Yunjun Gao and Ying Zhang},
journal= {arXiv preprint arXiv:2512.01610},
year = {2025}
}