A survey of multi-agent geosimulation methodologies: from ABM to LLM

TL;DR

This survey reviews multi-agent geosimulation methodologies, highlighting the integration of large language models as agents within a formal framework to enhance simulation platforms.

Contribution

It introduces a formal architecture for geosimulation platforms and demonstrates how LLMs can be effectively integrated as agents following this structure.

Findings

LLMs can serve as effective agent components in geosimulation.

A formal architecture for agent activities is proposed and validated.

The framework supports next-generation geosimulation systems.

Abstract

We provide a comprehensive examination of agent-based approaches that codify the principles and linkages underlying multi-agent systems, simulations, and information systems. Based on two decades of study, this paper confirms a framework intended as a formal specification for geosimulation platforms. Our findings show that large language models (LLMs) can be effectively incorporated as agent components if they follow a structured architecture specific to fundamental agent activities such as perception, memory, planning, and action. This integration is precisely consistent with the architecture that we formalize, providing a solid platform for next-generation geosimulation systems.