一句话：提出 InterDroid，通过多模态检索与记忆植入增强 LLM，实现跨应用 GUI 功能自动化测试并发现崩溃缺陷。
应用间功能需要多个应用协作完成，但现代应用动态更新且开放，基于预定义交互模型或历史数据的自动化 GUI 测试难以覆盖此类场景。LLM 驱动的测试方法又面临 UI 语义映射模糊和不可逆操作生成等问题。本文提出 InterDroid，通过将结构化语义知识植入 LLM 记忆来增强应用间测试。它使用融合视觉与文本 GUI 信息的模态检索方法获取相关历史交互，并设计记忆植入机制：全局记忆以对话形式呈现应用间路径，模拟先验测试经验；局部记忆跟踪实时状态转移。同时，测试监视器动态跟踪进度并检测偏差。InterDroid 作为可集成模块，在检测到应用切换时激活，并可在跨应用测试完成后让现有 GUI 测试工具无缝继续。在 63 个应用的 100 个应用间功能上评估，页面覆盖率提升最高 133%，动作覆盖率提升 124%，精确匹配准确率提升 268%；还发现 43 个新崩溃缺陷，其中 31 个已修复、12 个被开发者确认。
Inter-app functionality requires multiple apps to collaborate to complete a functional task, which has become essential in modern software ecosystems. However, due to the dynamic updates and openness of modern apps, automated GUI testing based on predefined interaction models or trained on historical data is difficult to achieve inter-app testing. The low fault tolerance and context-dependent characteristics of inter-app functionality paths, lead the LLM-based GUI testing to have UI semantic mapping ambiguity and irreversible operation generating problem. To address these challenges, this paper proposes InterDroid, an automated GUI testing approach that enhances inter-app testing by implanting structured semantic knowledge into LLM’s memory. InterDroid retrieves relevant historical inter-app interactions using a multimodal retrieval method that integrates visual and textual GUI information, significantly improving retrieval accuracy. Inspired by the research on memory implantation in cognitive psychology, we design a memory implanting mechanism: global memory presents inter-app paths in a conversational form, simulating prior testing experience, and local memory tracks real-time state transitions. Additionally, InterDroid proposes a testing monitor that dynamically tracks testing progress and detects deviations, ensuring comprehensive test execution. InterDroid is designed as an integrable module that activates upon detecting the transition of the app to another app, allowing existing automated GUI testing tools to continue seamlessly after inter-app testing is completed. We evaluate InterDroid on 100 inter-app functionalities across 63 apps, comparing it with state-of-the-art GUI testing baselines. InterDroid achieves up to 133% improvement in page coverage, 124% in action coverage, and 268% in exact match accuracy over the best baseline. Furthermore, InterDroid detects 43 new crash bugs in real-world apps from Google Play, with 31 fixed and 12 confirmed by developers.
@inproceedings{paperbot11706,
title = {Think Outside the Box: Automating Inter-App Functionality Testing via Memory Implanting and Reasoning},
author = {Mengzhuo Chen and Zhe Liu and Chunyang Chen and Junjie Wang and Yangguang Xue and Boyu Wu and Libin Wu and Qing Wang},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3764538}
}