Beyond Static GUI Agent: Evolving LLM-based GUI Testing via Dynamic Memory
This program is tentative and subject to change.
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 failure 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 categories. Results show that MemoDroid enhances GUI testing performance across five baseline methods, 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 real-world apps, with 35 confirmed fixes and 14 acknowledged by developers, showing its practical value in memory-driven GUI testing.
This program is tentative and subject to change.
Wed 19 NovDisplayed time zone: Seoul change
14:00 - 15:30 | |||
14:00 10mTalk | Adaptive and accessible user interfaces for seniors through model-driven engineering Journal-First Track Shavindra Wickramathilaka Monash University, John Grundy Monash University, Kashumi Madampe Monash University, Australia, Omar Haggag Monash University, Australia Link to publication DOI | ||
14:10 10mTalk | AppBDS: LLM-Powered Description Synthesis for Sensitive Behaviors in Mobile Apps Research Papers | ||
14:20 10mTalk | Large Language Models for Automated Web-Form-Test Generation: An Empirical Study Journal-First Track Tao Li Macau University of Science and Technology, Chenhui Cui Macau University of Science and Technology, Rubing Huang Macau University of Science and Technology (M.U.S.T.), Dave Towey University of Nottingham Ningbo China, Lei Ma The University of Tokyo & University of Alberta | ||
14:30 10mTalk | Beyond Static GUI Agent: Evolving LLM-based GUI Testing via Dynamic Memory Research Papers Mengzhuo Chen Institute of Software, Chinese Academy of Sciences, Zhe Liu Institute of Software, Chinese Academy of Sciences, Chunyang Chen TU Munich, Junjie Wang Institute of Software at Chinese Academy of Sciences, Yangguang Xue University of Chinese Academy of Sciences, Boyu Wu Institute of Software at Chinese Academy of Sciences, Yuekai Huang Institute of Software, Chinese Academy of Sciences, Libin Wu Institute of Software Chinese Academy of Sciences, Qing Wang Institute of Software at Chinese Academy of Sciences | ||
14:40 10mTalk | Who's to Blame? Rethinking the Brittleness of Automated Web GUI Testing from a Pragmatic Perspective Research Papers Haonan Zhang University of Waterloo, Kundi Yao University of Waterloo, Zishuo Ding The Hong Kong University of Science and Technology (Guangzhou), Lizhi Liao Memorial University of Newfoundland, Weiyi Shang University of Waterloo | ||
14:50 10mTalk | LLM-Cure: LLM-based Competitor User Review Analysis for Feature Enhancement Journal-First Track Maram Assi Université du Québec à Montréal, Safwat Hassan University of Toronto, Ying Zou Queen's University, Kingston, Ontario | ||
15:00 10mTalk | MIMIC: Integrating Diverse Personality Traits for Better Game Testing Using Large Language Model Research Papers Pre-print | ||
15:10 10mTalk | Debun: Detecting Bundled JavaScript Libraries on Web using Property-Order Graphs Research Papers Seojin Kim North Carolina State University, Sungmin Park Korea University, Jihyeok Park Korea University | ||
15:20 10mTalk | GUIFuzz++: Unleashing Grey-box Fuzzing on Desktop Graphical User Interfacing Applications Research Papers Pre-print | ||