PulseAugur
实时 15:28:27
English(EN) Cluster-Aware Dual-Level Test Specification Generation for Large-Scale Automotive Software Requirements

AI流水线自动化汽车软件测试规范生成

研究人员开发了一种新颖的“集群然后总结”流水线,用于自动化大规模汽车软件需求测试规范的生成。该方法嵌入需求,使用UMAP和HDBSCAN进行聚类,然后总结每个集群以保留关键信息。该流水线在单个需求和集群级集成点生成测试,与标准的LLM方法相比,提高了覆盖率和效率。 AI

排序理由 该集群包含一篇学术论文,详细介绍了AI在软件工程中的新应用方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Hazem Ayman, Menna Sedik, Kareem Mostafa, Mahmoud Soliman, Samer Saber, Ibrahim Habib ·

    Cluster-Aware Dual-Level Test Specification Generation for Large-Scale Automotive Software Requirements

    arXiv:2606.17197v1 Announce Type: cross Abstract: Generating test specifications that satisfy Automotive SPICE SWE.6 requirements becomes increasingly challenging and time-consuming as projects scale to thousands of requirements. Because this manual process often consumes weeks o…