LLM-Assisted Requirements Decomposition in Automotive Software Engineering - A Case Study at Volvo Cars

Abstract

Requirements decomposition in automotive software engineering is a complex and context-dependent activity that requires architectural understanding, abstraction level judgement, and domain expertise. Although Large Language Models (LLMs) have shown potential in several software engineering tasks, their use for requirements decomposition in safety-critical automotive contexts remains insufficiently understood. This thesis investigates how LLM-based assistants can support requirements decom position in automotive software engineering through a case study at Volvo Cars. The study follows a Design Science Research methodology combining semi-structured interviews, iterative artefact development, and industrial evaluation with domain experts. The resulting human-in-the-loop artefact combines contextual grounding through standards, historical decompositions, and system-structure information with hierarchy guidance, structured prompt orchestration, and schema-constrained generation. The artefact was evaluated through benchmark-based assessments, contextual evaluations using participant-selected requirements, and qualitative feedback sessions with automotive domain experts. The results suggest that LLM-based assistants can support requirements decomposition by reducing cognitive effort, improving contextual awareness, and providing alternative decomposition perspectives during refinement. The evaluation further indicates that contextual grounding, hierarchy guidance, and structured orchestration positively influenced expert-perceived out put quality and reviewability. At the same time, important limitations remain related to abstraction-level consistency, incomplete contextual understanding, and the need for expert validation in safety-critical engineering contexts. The findings suggest that LLM-based decomposition assistants are most useful as decision-support tools within human-in-the-loop workflows rather than as autonomous requirement generation systems.