一句话：提出并工业部署ARC-V多智能体系统，用LLM实现需求驱动的代码验证与早期缺陷发现。
在金融科技等受监管行业，需求模糊导致的晚期缺陷会显著增加修复成本。本文介绍ARC-V——在JPMorganChase部署的多智能体AI系统，通过将大语言模型用于自动化需求与代码验证，将质量保证前移。其专用智能体分别：依据组织标准评估需求工单并给出可操作整改指导；验证代码是否满足需求，预测缺陷并提供提交级反馈；持续监控智能体性能与采用情况。生产部署显示，用户故事中“价值声明”和“验收标准”字段的质量得分分别提升8.5分和4分；系统实现79%的早期缺陷发现率，在测试前识别出绝大多数逃逸至生产的缺陷。结果验证了以需求为中心、AI驱动的可扩展软件质量保证方法在复杂环境中的有效性。
Late-stage defect discovery, often rooted in ambiguous requirements, significantly increases remediation costs especially in regulated industries such as fintech. We present ARC-V, a multi-agent AI system deployed at JPMorganChase that shifts quality assurance upstream by operationalising Large Language Models for automated requirement and code verification. ARC-V utilizes specialised agents to (1) assess requirement tickets against organisational standards in order to provide actionable remedial guidance; (2) verify code against requirements in order to predict defects and offer commit-level feedback; (3) continuously monitor agent performance and adoption. Post-production deployment results at JPMorganChase show that ARC-V greatly increased the quality score of user story fields with 'value statements' and 'acceptance criteria' achieving score improvements of 8.5 and 4 points, respectively. Crucially, ARC-V achieved a 79% early defect discovery rate, identifying the vast majority of production-escaping bugs before testing. These results validate a requirements-centric, AI-driven approach to scalable software quality assurance in complex environments.
@inproceedings{BakerMMS26,
title = {Industrial Deployment of an AI Multi-Agent System for Requirements-Driven Code Verification},
author = {Paul Baker and Blanca Manu and Rebecca Moussa and Federica Sarro},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3805221}
}