arXiv subjects

Sidong Feng

Publications and source records attributed to Sidong Feng.

At least 19 recordsLinked to original sources

arXiv2026

ViBR: Automated Bug Replay from Video-based Reports using Vision-Language Models

Bug reports play a critical role in software maintenance by helping users convey encountered issues to developers. Recently, GUI screen capture videos have gained popularity as a bug reporting artifact due to their ease of use and ability to retain rich contextual information. However, automatically reproducing bugs from such recordings remains a significant challenge. Existing methods often rely on fragile image-processing heuristics, explicit touch indicators, or pre-constructed UI transition graphs, which require non-trivial instrumentation and app-specific setup. This paper presents ViBR, a lightweight and fully automated approach that reproduces bugs directly from GUI recordings. Specifically, ViBR combines CLIP-based embedding similarity for action boundary segmentation with Vision-Language Models (VLMs) for region-aware GUI state comparison and guided bug replay. Experimental results show that ViBR successfully reproduces 72% of bug recordings, significantly outperforming state-of-the-art baselines and ablation variants.

cs.SE↗

arXiv2026

How Smart Is Your GUI Agent? A Framework for the Future of Software Interaction

GUI agents are rapidly becoming a new interaction to software, allowing people to navigate web, desktop and mobile rather than execute them click by click. Yet ``agent'' is described with radically different degrees of autonomy, obscuring capability, responsibility and risk. We call for conceptual clarity through GUI Agent Autonomy Levels (GAL), a six-level framework that makes autonomy explicit and helps benchmark progress toward trustworthy software interaction.

cs.SE↗

arXiv2025

Breaking Single-Tester Limits: Multi-Agent LLMs for Multi-User Feature Testing

The growing dependence on mobile phones and their apps has made multi-user interactive features, like chat calls, live streaming, and video conferencing, indispensable for bridging the gaps in social connectivity caused by physical and situational barriers. However, automating these interactive features for testing is fraught with challenges, owing to their inherent need for timely, dynamic, and collaborative user interactions, which current automated testing methods inadequately address. Inspired by the concept of agents designed to autonomously and collaboratively tackle problems, we propose MAdroid, a novel multi-agent approach powered by the Large Language Models (LLMs) to automate the multi-user interactive task for app feature testing. Specifically, MAdroid employs two functional types of multi-agents: user agents (Operator) and supervisor agents (Coordinator and Observer). Each agent takes a specific role: the Coordinator directs the interactive task; the Operator mimics user interactions on the device; and the Observer monitors and reviews the task automation process. Our evaluation, which included 41 multi-user interactive tasks, demonstrates the effectiveness of our approach, achieving 82.9% of the tasks with 96.8% action similarity, outperforming the ablation studies and state-of-the-art baselines. Additionally, a preliminary investigation underscores MAdroid's practicality by helping identify 11 multi-user interactive bugs during regression app testing, confirming its potential value in real-world software development contexts.

cs.SE↗

arXiv2025

Agent for User: Testing Multi-User Interactive Features in TikTok

TikTok, a widely-used social media app boasting over a billion monthly active users, requires effective app quality assurance for its intricate features. Feature testing is crucial in achieving this goal. However, the multi-user interactive features within the app, such as live streaming, voice calls, etc., pose significant challenges for developers, who must handle simultaneous device management and user interaction coordination. To address this, we introduce a novel multi-agent approach, powered by the Large Language Models (LLMs), to automate the testing of multi-user interactive app features. In detail, we build a virtual device farm that allocates the necessary number of devices for a given multi-user interactive task. For each device, we deploy an LLM-based agent that simulates a user, thereby mimicking user interactions to collaboratively automate the testing process. The evaluations on 24 multi-user interactive tasks within the TikTok app, showcase its capability to cover 75% of tasks with 85.9% action similarity and offer 87% time savings for developers. Additionally, we have also integrated our approach into the real-world TikTok testing platform, aiding in the detection of 26 multi-user interactive bugs.

cs.SE↗

arXiv2025

An Empirical Study on Leveraging Images in Automated Bug Report Reproduction

Automated bug reproduction is a challenging task, with existing tools typically relying on textual steps-to-reproduce, videos, or crash logs in bug reports as input. However, images provided in bug reports have been overlooked. To address this gap, this paper presents an empirical study investigating the necessity of including images as part of the input in automated bug reproduction. We examined the characteristics and patterns of images in bug reports, focusing on (1) the distribution and types of images (e.g., UI screenshots), (2) documentation patterns associated with images (e.g., accompanying text, annotations), and (3) the functional roles they served, particularly their contribution to reproducing bugs. Furthermore, we analyzed the impact of images on the performance of existing tools, identifying the reasons behind their influence and the ways in which they can be leveraged to improve bug reproduction. Our findings reveal several key insights that demonstrate the importance of images in supporting automated bug reproduction. Specifically, we identified six distinct functional roles that images serve in bug reports, each exhibiting unique patterns and specific contributions to the bug reproduction process. This study offers new insights into tool advancement and suggests promising directions for future research.

cs.SE↗

arXiv2024

Towards Human-AI Synergy in UI Design: Supporting Iterative Generation with LLMs

In automated UI design generation, a key challenge is the lack of support for iterative processes, as most systems focus solely on end-to-end output. This stems from limited capabilities in interpreting design intent and a lack of transparency for refining intermediate results. To better understand these challenges, we conducted a formative study that identified concrete and actionable requirements for supporting iterative design with Generative Tools. Guided by these findings, we propose PrototypeFlow, a human-centered system for automated UI generation that leverages multi-modal inputs and models. PrototypeFlow takes natural language descriptions and layout preferences as input to generate the high-fidelity UI design. At its core is a theme design module that clarifies implicit design intent through prompt enhancement and orchestrates sub-modules for component-level generation. Designers retain full control over inputs, intermediate results, and final prototypes, enabling flexible and targeted refinement by steering generation and directly editing outputs. Our experiments and user studies confirmed the effectiveness and usefulness of our proposed PrototypeFlow.

cs.HC↗

arXiv2024

Enabling Cost-Effective UI Automation Testing with Retrieval-Based LLMs: A Case Study in WeChat

UI automation tests play a crucial role in ensuring the quality of mobile applications. Despite the growing popularity of machine learning techniques to generate these tests, they still face several challenges, such as the mismatch of UI elements. The recent advances in Large Language Models (LLMs) have addressed these issues by leveraging their semantic understanding capabilities. However, a significant gap remains in applying these models to industrial-level app testing, particularly in terms of cost optimization and knowledge limitation. To address this, we introduce CAT to create cost-effective UI automation tests for industry apps by combining machine learning and LLMs with best practices. Given the task description, CAT employs Retrieval Augmented Generation (RAG) to source examples of industrial app usage as the few-shot learning context, assisting LLMs in generating the specific sequence of actions. CAT then employs machine learning techniques, with LLMs serving as a complementary optimizer, to map the target element on the UI screen. Our evaluations on the WeChat testing dataset demonstrate the CAT's performance and cost-effectiveness, achieving 90% UI automation with $0.34 cost, outperforming the state-of-the-art. We have also integrated our approach into the real-world WeChat testing platform, demonstrating its usefulness in detecting 141 bugs and enhancing the developers' testing process.

cs.SE↗

arXiv2024

Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps

In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model (LLM), to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to Reproduce (S2R) entities. Instead, it leverages the entire textual bug report and employs innovative prompts to enhance GPT's contextual reasoning. This approach is more flexible and context-aware than the traditional step-by-step entity matching approach, resulting in improved accuracy and effectiveness. In addition to handling crash reports, ReBL has the capability of handling non-crash functional bug reports. Our evaluation of 96 Android bug reports (73 crash and 23 non-crash) demonstrates that ReBL successfully reproduced 90.63% of these reports, averaging only 74.98 seconds per bug report. Additionally, ReBL outperformed three existing tools in both success rate and speed.

cs.SE↗

arXiv2024

MUD: Towards a Large-Scale and Noise-Filtered UI Dataset for Modern Style UI Modeling

The importance of computational modeling of mobile user interfaces (UIs) is undeniable. However, these require a high-quality UI dataset. Existing datasets are often outdated, collected years ago, and are frequently noisy with mismatches in their visual representation. This presents challenges in modeling UI understanding in the wild. This paper introduces a novel approach to automatically mine UI data from Android apps, leveraging Large Language Models (LLMs) to mimic human-like exploration. To ensure dataset quality, we employ the best practices in UI noise filtering and incorporate human annotation as a final validation step. Our results demonstrate the effectiveness of LLMs-enhanced app exploration in mining more meaningful UIs, resulting in a large dataset MUD of 18k human-annotated UIs from 3.3k apps. We highlight the usefulness of MUD in two common UI modeling tasks: element detection and UI retrieval, showcasing its potential to establish a foundation for future research into high-quality, modern UIs.

cs.HC↗

arXiv2024

Prompting Is All You Need: Automated Android Bug Replay with Large Language Models

Bug reports are vital for software maintenance that allow users to inform developers of the problems encountered while using the software. As such, researchers have committed considerable resources toward automating bug replay to expedite the process of software maintenance. Nonetheless, the success of current automated approaches is largely dictated by the characteristics and quality of bug reports, as they are constrained by the limitations of manually-crafted patterns and pre-defined vocabulary lists. Inspired by the success of Large Language Models (LLMs) in natural language understanding, we propose AdbGPT, a new lightweight approach to automatically reproduce the bugs from bug reports through prompt engineering, without any training and hard-coding effort. AdbGPT leverages few-shot learning and chain-of-thought reasoning to elicit human knowledge and logical reasoning from LLMs to accomplish the bug replay in a manner similar to a developer. Our evaluations demonstrate the effectiveness and efficiency of our AdbGPT to reproduce 81.3% of bug reports in 253.6 seconds, outperforming the state-of-the-art baselines and ablation studies. We also conduct a small-scale user study to confirm the usefulness of AdbGPT in enhancing developers' bug replay capabilities.

cs.SE↗

arXiv2023

Designing with Language: Wireframing UI Design Intent with Generative Large Language Models

Wireframing is a critical step in the UI design process. Mid-fidelity wireframes offer more impactful and engaging visuals compared to low-fidelity versions. However, their creation can be time-consuming and labor-intensive, requiring the addition of actual content and semantic icons. In this paper, we introduce a novel solution WireGen, to automatically generate mid-fidelity wireframes with just a brief design intent description using the generative Large Language Models (LLMs). Our experiments demonstrate the effectiveness of WireGen in producing 77.5% significantly better wireframes, outperforming two widely-used in-context learning baselines. A user study with 5 designers further validates its real-world usefulness, highlighting its potential value to enhance UI design process.

cs.HC↗

arXiv2023

Towards Efficient Record and Replay: A Case Study in WeChat

WeChat, a widely-used messenger app boasting over 1 billion monthly active users, requires effective app quality assurance for its complex features. Record-and-replay tools are crucial in achieving this goal. Despite the extensive development of these tools, the impact of waiting time between replay events has been largely overlooked. On one hand, a long waiting time for executing replay events on fully-rendered GUIs slows down the process. On the other hand, a short waiting time can lead to events executing on partially-rendered GUIs, negatively affecting replay effectiveness. An optimal waiting time should strike a balance between effectiveness and efficiency. We introduce WeReplay, a lightweight image-based approach that dynamically adjusts inter-event time based on the GUI rendering state. Given the real-time streaming on the GUI, WeReplay employs a deep learning model to infer the rendering state and synchronize with the replaying tool, scheduling the next event when the GUI is fully rendered. Our evaluation shows that our model achieves 92.1% precision and 93.3% recall in discerning GUI rendering states in the WeChat app. Through assessing the performance in replaying 23 common WeChat usage scenarios, WeReplay successfully replays all scenarios on the same and different devices more efficiently than the state-of-the-practice baselines.

cs.SE↗

arXiv2023

Unveiling the Tricks: Automated Detection of Dark Patterns in Mobile Applications

Mobile apps bring us many conveniences, such as online shopping and communication, but some use malicious designs called dark patterns to trick users into doing things that are not in their best interest. Many works have been done to summarize the taxonomy of these patterns and some have tried to mitigate the problems through various techniques. However, these techniques are either time-consuming, not generalisable or limited to specific patterns. To address these issues, we propose UIGuard, a knowledge-driven system that utilizes computer vision and natural language pattern matching to automatically detect a wide range of dark patterns in mobile UIs. Our system relieves the need for manually creating rules for each new UI/app and covers more types with superior performance. In detail, we integrated existing taxonomies into a consistent one, conducted a characteristic analysis and distilled knowledge from real-world examples and the taxonomy. Our UIGuard consists of two components, Property Extraction and Knowledge-Driven Dark Pattern Checker. We collected the first dark pattern dataset, which contains 4,999 benign UIs and 1,353 malicious UIs of 1,660 instances spanning 1,023 mobile apps. Our system achieves a superior performance in detecting dark patterns (micro averages: 0.82 in precision, 0.77 in recall, 0.79 in F1 score). A user study involving 58 participants further shows that \tool{} significantly increases users' knowledge of dark patterns.

cs.HC↗

arXiv2023

Video2Action: Reducing Human Interactions in Action Annotation of App Tutorial Videos

Tutorial videos of mobile apps have become a popular and compelling way for users to learn unfamiliar app features. To make the video accessible to the users, video creators always need to annotate the actions in the video, including what actions are performed and where to tap. However, this process can be time-consuming and labor-intensive. In this paper, we introduce a lightweight approach Video2Action, to automatically generate the action scenes and predict the action locations from the video by using image-processing and deep-learning methods. The automated experiments demonstrate the good performance of Video2Action in acquiring actions from the videos, and a user study shows the usefulness of our generated action cues in assisting video creators with action annotation.

cs.HC↗

arXiv2023

Psychologically-Inspired, Unsupervised Inference of Perceptual Groups of GUI Widgets from GUI Images

Graphical User Interface (GUI) is not merely a collection of individual and unrelated widgets, but rather partitions discrete widgets into groups by various visual cues, thus forming higher-order perceptual units such as tab, menu, card or list. The ability to automatically segment a GUI into perceptual groups of widgets constitutes a fundamental component of visual intelligence to automate GUI design, implementation and automation tasks. Although humans can partition a GUI into meaningful perceptual groups of widgets in a highly reliable way, perceptual grouping is still an open challenge for computational approaches. Existing methods rely on ad-hoc heuristics or supervised machine learning that is dependent on specific GUI implementations and runtime information. Research in psychology and biological vision has formulated a set of principles (i.e., Gestalt theory of perception) that describe how humans group elements in visual scenes based on visual cues like connectivity, similarity, proximity and continuity. These principles are domain-independent and have been widely adopted by practitioners to structure content on GUIs to improve aesthetic pleasant and usability. Inspired by these principles, we present a novel unsupervised image-based method for inferring perceptual groups of GUI widgets. Our method requires only GUI pixel images, is independent of GUI implementation, and does not require any training data. The evaluation on a dataset of 1,091 GUIs collected from 772 mobile apps and 20 UI design mockups shows that our method significantly outperforms the state-of-the-art ad-hoc heuristics-based baseline. Our perceptual grouping method creates the opportunities for improving UI-related software engineering tasks.

cs.HC↗

arXiv2023

Efficiency Matters: Speeding Up Automated Testing with GUI Rendering Inference

Due to the importance of Android app quality assurance, many automated GUI testing tools have been developed. Although the test algorithms have been improved, the impact of GUI rendering has been overlooked. On the one hand, setting a long waiting time to execute events on fully rendered GUIs slows down the testing process. On the other hand, setting a short waiting time will cause the events to execute on partially rendered GUIs, which negatively affects the testing effectiveness. An optimal waiting time should strike a balance between effectiveness and efficiency. We propose AdaT, a lightweight image-based approach to dynamically adjust the inter-event time based on GUI rendering state. Given the real-time streaming on the GUI, AdaT presents a deep learning model to infer the rendering state, and synchronizes with the testing tool to schedule the next event when the GUI is fully rendered. The evaluations demonstrate the accuracy, efficiency, and effectiveness of our approach. We also integrate our approach with the existing automated testing tool to demonstrate the usefulness of AdaT in covering more activities and executing more events on fully rendered GUIs.

cs.SE↗

arXiv2023

Read It, Don't Watch It: Captioning Bug Recordings Automatically

Screen recordings of mobile applications are easy to capture and include a wealth of information, making them a popular mechanism for users to inform developers of the problems encountered in the bug reports. However, watching the bug recordings and efficiently understanding the semantics of user actions can be time-consuming and tedious for developers. Inspired by the conception of the video subtitle in movie industry, we present a lightweight approach CAPdroid to caption bug recordings automatically. CAPdroid is a purely image-based and non-intrusive approach by using image processing and convolutional deep learning models to segment bug recordings, infer user action attributes, and generate subtitle descriptions. The automated experiments demonstrate the good performance of CAPdroid in inferring user actions from the recordings, and a user study confirms the usefulness of our generated step descriptions in assisting developers with bug replay.

cs.SE↗

arXiv2022

GIFdroid: Automated Replay of Visual Bug Reports for Android Apps

Bug reports are vital for software maintenance that allow users to inform developers of the problems encountered while using software. However, it is difficult for non-technical users to write clear descriptions about the bug occurrence. Therefore, more and more users begin to record the screen for reporting bugs as it is easy to be created and contains detailed procedures triggering the bug. But it is still tedious and time-consuming for developers to reproduce the bug due to the length and unclear actions within the recording. To overcome these issues, we propose GIFdroid, a light-weight approach to automatically replay the execution trace from visual bug reports. GIFdroid adopts image processing techniques to extract the keyframes from the recording, map them to states in GUI Transitions Graph, and generate the execution trace of those states to trigger the bug. Our automated experiments and user study demonstrate its accuracy, efficiency, and usefulness of the approach.

cs.SE↗