LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study
This addresses workflow inefficiencies for domain experts and developers in multidisciplinary software development, offering an incremental improvement over existing AI coding assistants.
The paper tackled the inefficiency in Multidisciplinary Software Development by introducing a graph-based workflow optimization approach powered by LLMs, which reduced per-API development time from about 5 hours to under 7 minutes and achieved a 93.7% F1 score in a production automotive system.
Multidisciplinary Software Development (MSD) requires domain experts and developers to collaborate across incompatible formalisms and separate artifact sets. Today, even with AI coding assistants like GitHub Copilot, this process remains inefficient; individual coding tasks are semi-automated, but the workflow connecting domain knowledge to implementation is not. Developers and experts still lack a shared view, resulting in repeated coordination, clarification rounds, and error-prone handoffs. We address this gap through a graph-based workflow optimization approach that progressively replaces manual coordination with LLM-powered services, enabling incremental adoption without disrupting established practices. We evaluate our approach on \texttt{spapi}, a production in-vehicle API system at Volvo Group involving 192 endpoints, 420 properties, and 776 CAN signals across six functional domains. The automated workflow achieves 93.7\% F1 score while reducing per-API development time from approximately 5 hours to under 7 minutes, saving an estimated 979 engineering hours. In production, the system received high satisfaction from both domain experts and developers, with all participants reporting full satisfaction with communication efficiency.