LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins

TL;DR

This paper introduces a multi-agent system framework utilizing large language models to automate the parametrization of digital twin simulation models, improving usability and decision-making in complex systems.

Contribution

It proposes a novel LLM-based multi-agent system for autonomous exploration and parametrization of digital twin simulations, enhancing automation and user assistance.

Findings

Demonstrated effective autonomous parametrization in a case study

Reduced user cognitive load through LLM-driven decision support

System is accessible via open-source GitHub repository

Abstract

This paper presents a novel design of a multi-agent system framework that applies large language models (LLMs) to automate the parametrization of simulation models in digital twins. This framework features specialized LLM agents tasked with observing, reasoning, decision-making, and summarizing, enabling them to dynamically interact with digital twin simulations to explore parametrization possibilities and determine feasible parameter settings to achieve an objective. The proposed approach enhances the usability of simulation model by infusing it with knowledge heuristics from LLM and enables autonomous search for feasible parametrization to solve a user task. Furthermore, the system has the potential to increase user-friendliness and reduce the cognitive load on human users by assisting in complex decision-making processes. The effectiveness and functionality of the system are demonstrated through a case study, and the visualized demos and codes are available at a GitHub Repository: https://github.com/YuchenXia/LLMDrivenSimulation