一句话：用基于图的 LLM 服务工作流替代人工协调，在沃尔沃车用 API 系统上将单 API 开发时间从约 5 小时降至 7 分钟以内。
多学科软件开发（MSD）要求领域专家与开发者跨不兼容的形式体系和分离的工件集协作，但即便有 GitHub Copilot 等 AI 编码助手，连接领域知识与实现的工作流仍依赖人工协调，缺乏共享视图，导致反复澄清与易错交接。本文提出一种基于图的工作流优化方法，用 LLM 驱动的服务替代人工协调，并支持不打断既有实践的增量采纳。作者在 Volvo Group 的生产车用 API 系统 spapi 上评估，该系统覆盖六个功能域、192 个端点、420 个属性和 776 个 CAN 信号。自动化工作流达到 93.7% F1 分数，单 API 开发时间从约 5 小时降至 7 分钟以内，估计节省 979 工程小时；生产中领域专家与开发者满意度高，所有参与者均对沟通效率表示完全满意。
Multidisciplinary Software Development (MSD) requires domain experts and developers to collaborate across incompatible formalisms and separate artifact sets. 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, leading to repeated coordination, clarification rounds, and error-prone handoffs. We address this gap with a graph-based workflow optimization approach that replaces manual coordination with LLM-powered services, enabling incremental adoption without disrupting established practices. We evaluate our approach on 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.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2603-21439,
title = {LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study},
author = {Shuai Wang and Yinan Yu and Earl Barr and Dhasarathy Parthasarathy},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3805251}
}