From over-reliance to smart integration: using Large-Language Models as translators between specialized modeling and simulation tools

TL;DR

This paper proposes using Large Language Models as translators in modeling and simulation workflows to improve interoperability and reduce reliance on ambiguous natural language interfaces, ensuring more reliable and high-quality simulation processes.

Contribution

It introduces a novel framework for integrating LLMs as middleware in M&S, addressing key challenges in tool interoperability and proposing efficient architectures like Low-Rank Adaptation for task-specific adaptation.

Findings

LLMs can effectively act as translators between diverse modeling tools.

Structured integration improves interoperability and reduces ambiguity.

Low-Rank Adaptation architectures enable efficient LLM customization.

Abstract

Large Language Models (LLMs) offer transformative potential for Modeling & Simulation (M&S) through natural language interfaces that simplify workflows. However, over-reliance risks compromising quality due to ambiguities, logical shortcuts, and hallucinations. This paper advocates integrating LLMs as middleware or translators between specialized tools to mitigate complexity in M&S tasks. Acting as translators, LLMs can enhance interoperability across multi-formalism, multi-semantics, and multi-paradigm systems. We address two key challenges: identifying appropriate languages and tools for modeling and simulation tasks, and developing efficient software architectures that integrate LLMs without performance bottlenecks. To this end, the paper explores LLM-mediated workflows, emphasizes structured tool integration, and recommends Low-Rank Adaptation-based architectures for efficient task-specific adaptations. This approach ensures LLMs complement rather than replace specialized tools, fostering high-quality, reliable M&S processes.