Our paper From Over-Reliance to Smart Integration: Using Large-Language Models as Translators Between Specialized Modeling and Simulation Tools, co-authored with Philippe J. Giabbanelli (VMASC, Old Dominion, US), John Beverley (University of Buffalo, US), and Andreas Tolk (MITRE, US) has been accepted for the 2025 Winter Simulation Conference (WSC).
Preprint will be available soon.
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.