一句话：提出 MemoDroid，以三层动态记忆机制让 LLM 驱动的 GUI 测试积累并复用经验，显著提升覆盖率与缺陷检测。
针对 LLM 驱动的 GUI 测试孤立测试各应用、缺乏经验积累与复用，导致探索不深、难以触发易出错功能的问题，本文提出 MemoDroid——使测试智能体通过重复交互演化的三层记忆机制：情节记忆记录功能级测试轨迹，反思记忆总结问题模式与冗余行为，策略记忆合成跨应用探索策略；记忆在运行时动态注入 LLM 提示，以复用成功行为、避免无效动作并优先探索易出错路径。MemoDroid 以轻量插件实现，可集成现有方法。在 15 类真实应用上集成 5 个基线，Activity 与代码覆盖率提升 79%–96%、81%–97%，缺陷检测提升 57%–198%；消融验证各层贡献，并在 200 个流行应用中发现 49 个新缺陷。
The development of Large Language Models (LLMs) enables LLM-based GUI testing to interact with graphical user interfaces by understanding GUI screenshots and generating actions, which are widely applied in industry and academia. However, current approaches test each app in isolation, lacking mechanisms for experience accumulation and reuse. This limitation often causes GUI testing approaches to miss deeper exploration and fail to trigger bug-prone functionalities. To address this, we propose MemoDroid, a three-layer memory mechanism that augments LLM-based GUI testing with the ability to evolve through repeated interaction. MemoDroid designs episodic memory to capture functional-level testing traces, reflective memory to summarize issue patterns and redundant behaviors, and strategic memory to synthesize cross-app exploration strategies. These memory layers are dynamically retrieved and injected into LLM prompts at runtime, enabling the agent to reuse successful behaviors, avoid ineffective actions, and prioritize bug-prone paths. We implement MemoDroid as a lightweight plugin, which can be integrated into existing LLM-based GUI testing approaches. We evaluate MemoDroid on real-world apps from 15 diverse app categories. Results show that MemoDroid enhances GUI testing performance across five baselines, with activity and code coverage increasing by 79% - 96% and 81% - 97%, and bug detection improving by 57% - 198%. Ablation studies confirm the contributions of each memory layer. Furthermore, MemoDroid detects 49 new bugs in 200 popular apps, with 35 confirmed fixes and 14 acknowledged by developers, showing its practical value in memory-driven GUI testing.
DOI 原文 ·
@inproceedings{paperbot9484,
title = {Beyond Static GUI Agent: Evolving LLM-based GUI Testing via Dynamic Memory},
author = {Mengzhuo Chen and Zhe Liu and Chunyang Chen and Junjie Wang and Yangguang Xue and Boyu Wu and Yuekai Huang and Libin Wu and Qing Wang},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00135}
}