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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Giabbanelli, Philippe J., Beverley, John, David, Istvan, Tolk, Andreas
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912427302453248
author Giabbanelli, Philippe J.
Beverley, John
David, Istvan
Tolk, Andreas
author_facet Giabbanelli, Philippe J.
Beverley, John
David, Istvan
Tolk, Andreas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11141
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From over-reliance to smart integration: using Large-Language Models as translators between specialized modeling and simulation tools
Giabbanelli, Philippe J.
Beverley, John
David, Istvan
Tolk, Andreas
Software Engineering
Emerging Technologies
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.
title From over-reliance to smart integration: using Large-Language Models as translators between specialized modeling and simulation tools
topic Software Engineering
Emerging Technologies
url https://arxiv.org/abs/2506.11141