Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs
By: Yuren Mao , Peigen Liu , Xinjian Wang and more
Potential Business Impact:
Builds better computer worlds with changing characters.
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.
Similar Papers
KG-MAS: Knowledge Graph-Enhanced Multi-Agent Infrastructure for coupling physical and digital robotic environments
Multiagent Systems
Connects machines and computers for smarter factories.
STARK: Strategic Team of Agents for Refining Kernels
Artificial Intelligence
AI makes computer graphics run much faster.
Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation
Software Engineering
Builds complex computer programs automatically.