Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Shuai Wang, Yinan Yu, Earl Barr, Dhasarathy Parthasarathy

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.

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

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.
Paper Structure (39 sections, 5 equations, 6 figures, 9 tables)

This paper contains 39 sections, 5 equations, 6 figures, 9 tables.

Table of Contents

  1. Introduction
  2. The spapi System
  3. Observed Problems
  4. Industry Implications
  5. Our Approach
  6. Methods and Implementation
  7. Workflow Graph Representation
  8. Workflow Optimization Framework
  9. Node-level Transformation
  10. Graph-level Restructuring
  11. Measuring Transformation Impact
  12. Node-Level Automation
  13. Signal R/W Synthesis
  14. Signal-Property Synthesis
  15. Property-Endpoint Synthesis
  16. ...and 24 more sections

Figures (6)

  • Figure 1: Comparison of workflows in the Multidisciplinary Software Development (MSD) process: (a) a typical MSD workflow and (b) optimized workflow through automated translation via our graph-based approach.
  • Figure 2: Iterative workflow optimization framework for vehicle API generation. The upper part illustrates graph-level optimization, depicting how the initial manual workflow undergoes three iterative refinements to achieve a highly automated workflow. The lower-right part illustrates the final deployed workflow, which comprises three server nodes. The lower-left part illustrates the detailed structure of each node.
  • Figure 3: A simplified DSPy signature for Signal R/W Synthesis. The LLM generates Python functions to read or write CAN signals based on signal metadata.
  • Figure 4: Representative prompt used in the Signal-Property matching task (simplified for clarity).
  • Figure 5: Example of a FastAPI endpoint boilerplate template.
  • ...and 1 more figures