SysTemp: A Multi-Agent System for Template-Based Generation of SysML v2

2025/06/20 by Yasmine Bouamra, Bouamra, Yasmine, Bruno Yun +5
Business, Management and Accounting · Engineering · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Digital Transformation in Industry #FOS: Computer and information sciences #Service and Product Innovation #Systems Engineering Methodologies and Applications

paper · pdf · doi:10.48550/arxiv.2506.21608

openalex publication_date 2025/06/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The automatic generation of SysML v2 models represents a major challenge in the engineering of complex systems, particularly due to the scarcity of learning corpora and complex syntax. We present SysTemp, a system aimed at facilitating and improving the creation of SysML v2 models from natural language specifications. It is based on a multi-agent system, including a template generator that structures the generation process. We discuss the advantages and challenges of this system through an evaluation, highlighting its potential to improve the quality of the generations in SysML v2 modeling.

Citations

• How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMs
• Why Does the Effective Context Length of LLMs Fall Short?
• A Survey on Large Language Models for Code Generation
• Gemma: Open Models Based on Gemini Research and Technology
• Boosting Large Language Model for Speech Synthesis: An Empirical Study
• Task Contamination: Language Models May Not Be Few-Shot Anymore
• A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
• Towards Automatic Model Completion: from Requirements to SysML State Machines
• Evaluating Large Language Models Trained on Code
• On the Dangers of Stochastic Parrots
• Language Models are Few-Shot Learners

Related

• Text to model via SysML: Automated generation of dynamical system computational models from unstructured natural language text via enhanced System Modeling Language diagrams
• Model-Driven Engineering Method to Support the Formalization of Machine Learning using SysML
• SysMoBench: Evaluating AI on Formally Modeling Complex Real-World Systems
• A System Model Generation Benchmark from Natural Language Requirements
• Integrating AI Planning Semantics into SysML System Models for Automated PDDL File Generation