Simulation Agent: A Framework for Integrating Simulation and Large Language Models for Enhanced Decision-Making

TL;DR

This paper presents a simulation agent framework that combines the interactive language capabilities of large language models with the detailed accuracy of simulation systems to improve decision-making and user accessibility across various domains.

Contribution

The paper introduces a novel framework that seamlessly integrates simulation models with large language models, enhancing user interaction and grounding LLMs in real-world dynamics.

Findings

Enables intuitive interaction with complex simulations

Grounds LLM responses in accurate simulation data

Broad applicability across multiple domains

Abstract

Simulations, although powerful in accurately replicating real-world systems, often remain inaccessible to non-technical users due to their complexity. Conversely, large language models (LLMs) provide intuitive, language-based interactions but can lack the structured, causal understanding required to reliably model complex real-world dynamics. We introduce our simulation agent framework, a novel approach that integrates the strengths of both simulation models and LLMs. This framework helps empower users by leveraging the conversational capabilities of LLMs to interact seamlessly with sophisticated simulation systems, while simultaneously utilizing the simulations to ground the LLMs in accurate and structured representations of real-world phenomena. This integrated approach helps provide a robust and generalizable foundation for empirical validation and offers broad applicability across diverse domains.