Automatisierte Generierung von Simulationsmodellen für Produktions- und Logistikprozesse mithilfe LLM-basierter Multi-Agenten-Systeme
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
Simulation in Produktion und Logistik 2025: 21. ASIM-Fachtagung. ed. / Sebastian Rank; Mathias Kühn; Thorsten Schmidt. Dresden: Dresden University of Technology, 2025. 57.
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Automatisierte Generierung von Simulationsmodellen für Produktions- und Logistikprozesse mithilfe LLM-basierter Multi-Agenten-Systeme
AU - Krämer, Roman
AU - Heger, Jens
PY - 2025/10/21
Y1 - 2025/10/21
N2 - Discrete-event simulation (DES) is a well-established method for analyzing and optimizing complex production and logistics systems. However, its use is often limited by high modeling effort and the need for specialized expertise. This paper presents a novel multi-agent system based on Large Language Models (LLMs) that automates the creation and validation of simulation models. Building on a previous approach of ours, the new system employs an agent-based architecture designed to address issues such as context loss and the need for manual validation. Specialized agents handle tasks from requirements elicitation to results evaluation. The implementation uses open source frameworks 'LangGraph' to structure agent interactions and 'SimPy' to model the simulation logic. A case study demonstrates that the system can automatically and reproducibly model a complete production scenario from text-based descriptions. The results show realistic modeling and a significantly reduced modeling effort compared to both a manual approach and our previous system. The proposed approach lowers reliance on expert knowledge and makes simulation-based methods more accessible to non-specialist users.
AB - Discrete-event simulation (DES) is a well-established method for analyzing and optimizing complex production and logistics systems. However, its use is often limited by high modeling effort and the need for specialized expertise. This paper presents a novel multi-agent system based on Large Language Models (LLMs) that automates the creation and validation of simulation models. Building on a previous approach of ours, the new system employs an agent-based architecture designed to address issues such as context loss and the need for manual validation. Specialized agents handle tasks from requirements elicitation to results evaluation. The implementation uses open source frameworks 'LangGraph' to structure agent interactions and 'SimPy' to model the simulation logic. A case study demonstrates that the system can automatically and reproducibly model a complete production scenario from text-based descriptions. The results show realistic modeling and a significantly reduced modeling effort compared to both a manual approach and our previous system. The proposed approach lowers reliance on expert knowledge and makes simulation-based methods more accessible to non-specialist users.
U2 - 10.25368/2025.290
DO - 10.25368/2025.290
M3 - Aufsätze in Konferenzbänden
BT - Simulation in Produktion und Logistik 2025
A2 - Rank, Sebastian
A2 - Kühn, Mathias
A2 - Schmidt, Thorsten
PB - Dresden University of Technology
CY - Dresden
T2 - 21. ASIM-Fachtagung Simulation in Produktion und Logistik
Y2 - 24 September 2025 through 26 September 2025
ER -