DragonCrawl：基于意图的生成式移动端到端测试框架
原标题：DragonCrawl: A Generative, Intent-Based Framework for Scalable Mobile End-to-End Testing
AI 摘要
DragonCrawl 是一个基于大语言模型的移动端端到端测试框架，从嵌入相似度匹配演进到生成式意图推理，利用 GPT-4o 的多模态能力在 CI/CD 中持续验证用户流程。该系统在 iOS 和 Android 上分别达到 91.6% 和 92.2% 的通过率，将测试接入时间从 96-120 小时缩短至 4 小时以内，并节省了约 27 人年的维护工作量。论文还讨论了 token 爆炸和内存限制等挑战，展示了 AI 驱动测试在规模化持续质量保障中的有效性。
正文节选
Computer Science > Software Engineering Title:DragonCrawl: A Generative, Intent-Based Framework for Scalable Mobile End-to-End Testing View PDF HTML (experimental) Abstract:As mobile applications grow in complexity, traditional End-to-End (E2E) testing frameworks struggle with UI volatility, maintenance overhead, and cross-platform scalability. This paper presents DragonCrawl, an AI-driven mobile testing system for continuous regression testing that has evolved from embedding-based s