Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs

TL;DR

Agent-Kernel introduces a modular multi-agent system framework that enhances adaptability, configurability, and reusability for large-scale social simulations powered by LLMs, demonstrated through diverse complex scenarios.

Contribution

It presents a novel society-centric microkernel architecture that decouples core functions from simulation logic, improving flexibility and scalability in social simulations.

Findings

Successfully simulated rapid population changes in the Universe 25 experiment.

Coordinated 10,000 heterogeneous agents in a large-scale campus simulation.

Demonstrated superior adaptability and reusability over existing frameworks.

Abstract

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.