用大模型优化跨领域软件开发流程，显著提升协作效率。
LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study
- 基于图结构的工作流优化，用大模型替代人工协调。
- 实现93.7%的F1得分，单接口开发时间从5小时降至7分钟。
- 适合汽车电子等多领域协同开发场景，尤其适合需频繁沟通的团队。
多学科软件开发（MSD）需要领域专家与开发者在不兼容的形式化语言和独立的产物集之间协作。尽管已有GitHub Copilot等AI编程助手，但任务间的流程衔接仍依赖人工，导致重复协调、澄清和易出错的交接。本文提出一种基于图的工作流优化方法，逐步以大模型服务替代人工协调，支持渐进式采用且不影响现有流程。我们在沃尔沃集团的生产级车载API系统spapi上评估该方法，该系统包含192个端点、420个属性和776个CAN信号，覆盖六个功能域。自动化工作流达到93.7%的F1分数，单接口开发时间从约5小时缩短至7分钟以内，预计节省979名工程师工时。上线后，领域专家与开发人员均高度满意，所有参与者表示沟通效率完全满足需求。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。