arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.04500cs.AI
收藏

GUITester: 使GUI代理用于探索性缺陷发现

GUITester: Enabling GUI Agents for Exploratory Defect Discovery

Beijing Jiaotong University(北京交通大学);Hithink Research(慧思科技);Nanyang Technological University(南洋理工大学)

Yifei Gao, Jiang Wu, Xiaoyi Chen, Yifan Yang, Zhe Cui, Tianyi Ma, Jiaming Zhang, Jitao Sang

AI总结:

GUITester通过解耦导航与验证的多代理框架,有效解决了探索性GUI测试中目标导向遮蔽和执行偏差归因的问题,实现了48.90%的F1分数。

摘要:

探索性GUI测试对于软件质量至关重要,但存在高昂的人工成本。尽管多模态大语言模型(MLLM)代理在导航方面表现优异,但它们由于两个核心挑战而无法自主发现缺陷:目标导向的遮蔽,即代理优先完成任务而非报告异常,以及执行偏差归因,即系统缺陷被错误地识别为代理错误。为了解决这些问题,我们首先引入了GUITestBench,这是首个针对此任务的交互性基准,包含26种缺陷的143个任务。然后我们提出了GUITester,一个多代理框架,通过两个模块将导航与验证解耦:(i)一个规划-执行模块(PEM),通过嵌入的测试意图主动探测缺陷;(ii)一个分层反思模块(HRM),通过交互历史分析解决归因模糊性。GUITester在GUITestBench上实现了48.90%的F1分数(Pass@3),优于最先进的基线(33.35%)。我们的工作展示了自主探索性测试的可行性,并为未来的GUI质量保证提供了稳健的基础。

英文摘要:

Exploratory GUI testing is essential for software quality but suffers from high manual costs. While Multi-modal Large Language Model (MLLM) agents excel in navigation, they fail to autonomously discover defects due to two core challenges: \textit{Goal-Oriented Masking}, where agents prioritize task completion over reporting anomalies, and \textit{Execution-Bias Attribution}, where system defects are misidentified as agent errors. To address these, we first introduce \textbf{GUITestBench}, the first interactive benchmark for this task, featuring 143 tasks across 26 defects. We then propose \textbf{GUITester}, a multi-agent framework that decouples navigation from verification via two modules: (i) a \textit{Planning-Execution Module (PEM)} that proactively probes for defects via embedded testing intents, and (ii) a \textit{Hierarchical Reflection Module (HRM)} that resolves attribution ambiguity through interaction history analysis. GUITester achieves an F1-score of 48.90\% (Pass@3) on GUITestBench, outperforming state-of-the-art baselines (33.35\%). Our work demonstrates the feasibility of autonomous exploratory testing and provides a robust foundation for future GUI quality assurance~\footnote{Our code is now available in~\href{https://github.com/ADaM-BJTU/GUITestBench}{https://github.com/ADaM-BJTU/GUITestBench}}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑