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

arXiv: https://arxiv.org/abs/2603.21439 · HTML: https://mlsanity.com/paper/2603.21439/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 22 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [SynCode: LLM Generation with Grammar Augmentation](https://mlsanity.com/paper/2403.01632/) (2024)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [The future of human-AI collaboration: a taxonomy of design knowledge for hybrid intelligence systems](https://mlsanity.com/paper/2105.03354/) (2021)
- [How AI Developers Overcome Communication Challenges in a Multidisciplinary Team: A Case Study](https://mlsanity.com/paper/2101.06098/) (2021)
- [Leveraging Large Language Models to Improve REST API Testing](https://mlsanity.com/paper/2312.00894/) (2023)
- [Prototyping with Prompts: Emerging Approaches and Challenges in Generative AI Design for Collaborative Software Teams](https://mlsanity.com/paper/2402.17721/) (2024)
- [A Framework for Testing and Adapting REST APIs as LLM Tools](https://mlsanity.com/paper/2504.15546/) (2025)
- [Human and Machine: How Software Engineers Perceive and Engage with AI-Assisted Code Reviews Compared to Their Peers](https://mlsanity.com/paper/2501.02092/) (2025)
- [Automating a Complete Software Test Process Using LLMs: An Automotive Case Study](https://mlsanity.com/paper/2502.04008/) (2025)
- [iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answering](https://mlsanity.com/paper/2506.01784/) (2025)
- [Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance](https://mlsanity.com/paper/2506.04427/) (2025)
- [LLM-Generated Microservice Implementations from RESTful API Definitions](https://mlsanity.com/paper/2502.09766/) (2025)
- [Automotive Perception Software Development: An Empirical Investigation into Data, Annotation, and Ecosystem Challenges](https://mlsanity.com/paper/2303.05947/) (2023)
- [LRASGen: LLM-based RESTful API Specification Generation](https://mlsanity.com/paper/2504.16833/) (2025)
- [Towards Effective Collaboration between Software Engineers and Data Scientists developing Machine Learning-Enabled Systems](https://mlsanity.com/paper/2407.15821/) (2024)
- [When Domains Collide: An Activity Theory Exploration of Cross-Disciplinary Collaboration](https://mlsanity.com/paper/2506.20063/) (2025)
- [Domain-Adapted Pre-trained Language Models for Implicit Information Extraction in Crash Narratives](https://mlsanity.com/paper/2510.09434/) (2025)

## Abstract (arXiv)

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 textttspapi, 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.