一句话：DragonCrawl 用 GPT-4o 多模态生成式意图推理替代脆弱的移动 E2E 测试，实现大规模 CI/CD 回归验证。
移动应用日益复杂，传统端到端测试受困于 UI 易变、维护开销大与跨平台扩展难。DragonCrawl 是一个面向持续回归测试的 AI 驱动移动测试系统，从 V1 的嵌入相似度匹配演进为 V2 基于大语言模型的生成式意图推理。与以往聚焦探索性测试和崩溃检测的 LLM 测试研究不同，它在每次代码变更时验证特定用户流程，并阻断破坏关键功能的提交。系统利用 GPT-4o 的多模态能力，结合视觉终态检测与工具调用处理后端状态转换，在 CI/CD 中持续运行 1,013 个自动化测试，iOS 通过率 91.6%、Android 92.2%，将测试接入时间从 96–120 小时降至 4 小时以内，并节省约 27 开发者年的维护工作量。
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 similarity matching to generative intent-based reasoning using large language models. Unlike prior LLM-based testing research focused on exploratory testing and crash detection, DragonCrawl validates specific user flows on every code change, blocking commits that break critical functionality. By leveraging GPT-4o’s multimodal capabilities, DragonCrawl achieves 91.6% pass rate on iOS and 92.2% on Android across 1,013 automated tests running continuously in CI/CD pipelines. The system reduces test onboarding time from 96-120 hours to under 4 hours and has saved an estimated 27 developer years in test maintenance effort. We present the architectural evolution from V1 (semantic embedding matching) to V2 (generative intent-based reasoning), discuss implementation challenges including token explosion and memory constraints, and report operational experience from production deployment. The integration of multimodal vision for end-state detection and tool calling for backend state transitions enables comprehensive regression testing that bridges UI interactions with system state. Our results demonstrate that AI-driven testing can maintain stability while eliminating the brittleness of traditional automated tests, enabling continuous quality assurance at scale.
@inproceedings{abs-2607-28750,
title = {DragonCrawl: A Generative, Intent-Based Framework for Scalable Mobile End-to-End Testing},
author = {Sowjanya Puligadda and Mengdie Zhang and Ali Zamani and Dhruva Dixith Kurra and Eric Chen and Juan Marcano},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834455}
}