Automated AADL Architecture Modeling: Leveraging Large Language Models for Safety-Critical Software

Yaxin Zou, Zhibin Yang, Hao Liu, Jiawei Liang, Yong Zhou, Zonghua Gu

Abstract: Architecture modeling is an essential part of model-driven development of safety-critical software. AADL is a modeling language standard for designing and analyzing safety-critical software. However, there is usually a large gap between software requirements and architectural design. Effectively transforming requirements into formal software architecture models relies on a lot of manual experience and iterative exploration. To address these challenges, we conduct an exploratory study of LLM-supported AADL architecture modeling. We assess three powerful LLMs, GPT-4o, DeepSeekV3, and GLM-4-Plus. First, we decompose and refine high-level software requirements and design constraints, mapping them to the proposed prompt engineering framework, RNL-Prompt, which significantly improved the accuracy of LLMs in generating different modeling elements. Our findings reveal that GPT-4o and DeepSeek-V3 perform on par with each other, and both outperform GLM-4-Plus in complex modeling elements, such as modes, behavior annex, etc. Second, to enhance the potential of GLM-4-Plus, we optimize its performance using N-shot prompting and retrievalaugmented generation (RAG). The results indicate that N-shot prompting performs more effectively. Finally, we demonstrate the effectiveness of our proposed approach in generating AADL architecture models in five examples of safety-critical domains. In addition, we implement an LLM-based modeling tool based on the AADL open source environment OSATE, which supports GPT-4o, DeepSeek-V3, and GLM-4-Plus. The tool is successfully applied to the modeling of an avionics control system in the industry.

External IDs:dblp:conf/models/ZouYLLZG25