用智能体与混合向量图结构自动生成软件测试方案，提速降本。
Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration
- 构建多智能体协同系统，融合向量与图谱知识库提升上下文理解。
- 测试生成准确率从65%提升至94.8%，测试周期缩短85%。
- 适合企业级质量工程团队，尤其适用于大型系统迁移项目。
我们提出一种基于智能体增强型检索生成（Agentic RAG）的软件测试自动化方法，用于质量工程（QE）文档的自动生成。通过结合自主AI智能体与混合向量-图谱知识系统，实现测试计划、测试用例及质量度量指标的自动化生成。该方法利用Gemini、Mistral等大语言模型，配合多智能体编排机制与增强上下文建模能力，有效克服传统测试流程的局限性。实验验证显示，在企业级企业系统工程与SAP迁移项目中，测试生成准确率从65%提升至94.8%，测试周期缩短85%，测试套件效率提高85%，预计可节省35%成本，整体上线时间提前2个月。
原文摘要 · Abstract (English)
We present an approach to software testing automation using Agentic Retrieval-Augmented Generation (RAG) systems for Quality Engineering (QE) artifact creation. We combine autonomous AI agents with hybrid vector-graph knowledge systems to automate test plan, case, and QE metric generation. Our approach addresses traditional software testing limitations by leveraging LLMs such as Gemini and Mistral, multi-agent orchestration, and enhanced contextualization. The system achieves remarkable accuracy improvements from 65% to 94.8% while ensuring comprehensive document traceability throughout the quality engineering lifecycle. Experimental validation of enterprise Corporate Systems Engineering and SAP migration projects demonstrates an 85% reduction in testing timeline, an 85% improvement in test suite efficiency, and projected 35% cost savings, resulting in a 2-month acceleration of go-live.
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。