From Redundancy to Efficiency: Exploiting Shared UI Interactions towards Efficient LLM-Based Testing
This program is tentative and subject to change.
Redundant test cases, although well-studied in software engineering, are previously underexplored in UI testing of mobile apps. Our study of real-world test suites shows that, in large-scale testing suites, redundancy in UI testing often manifests as redundant UI interactions. Although negligible in traditional script-based workflows, such redundancy severely impacts the efficiency of emerging Large Language Model (LLM)-based UI agents, which incur substantial decision latency and token costs from repeated LLM queries for the same interactions. To this end, based on the idea of reusing LLMs’ former decisions, we present TestWeaver, a cost-effective LLM-based testing framework. Leveraging a semantically annotated UI Transition Graph (UTG), TestWeaver is capable of detecting shared interactions across test cases. It processes each interaction with a single LLM query and reuses the result whenever the same interaction occurs. We evaluate TestWeaver on real-world test suites from Meituan. It achieves a 92% success rate with an average cost of $0.11 and 89.7 seconds per case, outperforming the state of the art. We have also deployed TestWeaver in a real-world testing workflow at Meituan for over six months. TestWeaver has executed nearly 2,000 test cases and uncovered 10 previously undetected bugs, while reducing manual testing effort by 75%.
This program is tentative and subject to change.
Wed 19 NovDisplayed time zone: Seoul change
16:00 - 17:00 | |||
16:00 10mTalk | Minuku: Detecting Diverse Display Issues in Mobile Apps with Small-scale Dataset Industry Showcase Yongxiang Hu Fudan University, Ke Liu College of Computer Science and Artificial Intelligence, Fudan University, Hailiang Jin Meituan Inc., Shiyu Guo Meituan, Juxing Yuan Meituan Inc., Xin Wang Fudan University, Yangfan Zhou Fudan University | ||
16:10 10mTalk | HarmoBridge: Bridging ArkTS and C/C++ for Cross-Language Static Analysis on HarmonyOS Industry Showcase Jiale Wu Huazhong University of Science and Technology, Jiapeng Deng Huazhong University of Science and Technology, Yanjie Zhao Huazhong University of Science and Technology, Li Li Beihang University, Haoyu Wang Huazhong University of Science and Technology | ||
16:20 10mTalk | From Redundancy to Efficiency: Exploiting Shared UI Interactions towards Efficient LLM-Based Testing Industry Showcase Xuan Wang Fudan University, Yingchuan Wang School of Computer Science, Fudan University, Yongxiang Hu Fudan University, Yu Zhang Meituan, Hailiang Jin Meituan Inc., Shiyu Guo Meituan, Juxing Yuan Meituan Inc., Yangfan Zhou Fudan University | ||
16:30 10mTalk | Securing Millions of Decentralized Identities in Alipay Super App with End-to-End Formal Verification Industry Showcase Ziyu Mao Zhejiang University, Xiaolin Ma Zhejiang University, Lin Huang Ant Group, Huan Yang Ant Group, Wu Zhang Ant Group, Weichao Sun Ant Group, Yongtao Wang Ant Group, Jingling Xue University of New South Wales, Jingyi Wang Zhejiang University | ||
16:40 10mTalk | LLM-based Dynamic Differential Testing for Database Connectors with Reinforcement Learning-Guided Prompt Selection NIER Track Ce Lyu East China Normal University, Yanhao Wang East China Normal University, Jie Liang Beihang University, Minghao Zhao East China Normal University | ||
16:50 10mTalk | LLM-assisted Industrial-Scale Differential Testing of Package Incompatibilities in Linux Distributions Industry Showcase Yuhao Yang Central South University, Chijin Zhou East China Normal University, Runzhe Wang Alibaba Group, Weibo Zhang Central South University, Yuheng Shen Tsinghua University, Xiaohai Shi Alibaba Group, Tao Ma Alibaba Group, Chang Gao Alibaba Group, Zhe Wang Institute of Computing Technology at Chinese Academy of Sciences; Zhongguancun Laboratory, Ying Fu Tsinghua University, Heyuan Shi Central South University | ||