LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study

2026-03-22

AI Summary

This work addresses the inefficiencies and handoff errors in multidisciplinary software development caused by incompatible formalisms and fragmented artifacts between domain experts and developers. To bridge this gap, we propose a graph-structured workflow optimization method that integrates large language models (LLMs) into the development pipeline for the first time. By leveraging semantic alignment, requirement parsing, and code generation, our approach automatically connects domain knowledge with implementation logic. The method supports incremental deployment without disrupting existing practices. Evaluation on Volvo Group’s spapi in-vehicle API system demonstrates an F1 score of 93.7%, reduces per-API development time from five hours to seven minutes, saves a total of 979 engineering hours, and achieves 100% user satisfaction.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

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.

Problem

• Multidisciplinary Software Development
• workflow inefficiency
• domain-developer collaboration
• knowledge handoff
• shared understanding

Innovation

• LLM-powered workflow
• graph-based optimization
• multidisciplinary software development
• automotive API automation
• domain-developer collaboration