arXiv subjects

Zhenchang Xing

Publications and source records attributed to Zhenchang Xing.

At least 55 records · Page 3Linked to original sources

arXiv2025

LLM-as-a-Judge for Software Engineering: Literature Review, Vision, and the Road Ahead

The rapid integration of Large Language Models (LLMs) into software engineering (SE) has revolutionized tasks like code generation, producing a massive volume of software artifacts. This surge has exposed a critical bottleneck: the lack of scalable, reliable methods to evaluate these outputs. Human evaluation is costly and time-consuming, while traditional automated metrics like BLEU fail to capture nuanced quality aspects. In response, the LLM-as-a-Judge paradigm - using LLMs for automated evaluation - has emerged. This approach leverages the advanced reasoning of LLMs, offering a path toward human-like nuance at automated scale. However, LLM-as-a-Judge research in SE is still in its early stages. This forward-looking SE 2030 paper aims to steer the community toward advancing LLM-as-a-Judge for evaluating LLM-generated software artifacts. We provide a literature review of existing SE studies, analyze their limitations, identify key research gaps, and outline a detailed roadmap. We envision these frameworks as reliable, robust, and scalable human surrogates capable of consistent, multi-faceted artifact evaluation by 2030. Our work aims to foster research and adoption of LLM-as-a-Judge frameworks, ultimately improving the scalability of software artifact evaluation.

cs.SE↗

arXiv2025

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

In this paper we tackle a fundamental question: "Can we train latent diffusion models together with the variational auto-encoder (VAE) tokenizer in an end-to-end manner?" Traditional deep-learning wisdom dictates that end-to-end training is often preferable when possible. However, for latent diffusion transformers, it is observed that end-to-end training both VAE and diffusion-model using standard diffusion-loss is ineffective, even causing a degradation in final performance. We show that while diffusion loss is ineffective, end-to-end training can be unlocked through the representation-alignment (REPA) loss -- allowing both VAE and diffusion model to be jointly tuned during the training process. Despite its simplicity, the proposed training recipe (REPA-E) shows remarkable performance; speeding up diffusion model training by over 17x and 45x over REPA and vanilla training recipes, respectively. Interestingly, we observe that end-to-end tuning with REPA-E also improves the VAE itself; leading to improved latent space structure and downstream generation performance. In terms of final performance, our approach sets a new state-of-the-art; achieving FID of 1.12 and 1.69 with and without classifier-free guidance on ImageNet 256 x 256. Code is available at https://end2end-diffusion.github.io.

cs.CV↗

arXiv2025

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities

Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While language model agents show promise in cybersecurity, modern web applications demand visual understanding, dynamic content handling, and multi-step interactions that only computer-use agents (CUAs) can perform. Yet, their ability to discover and exploit vulnerabilities through graphical interfaces remains largely unexplored. We present HackWorld, the first framework for systematically evaluating CUAs' capabilities to exploit web application vulnerabilities via visual interaction. Unlike sanitized benchmarks, HackWorld includes 36 real-world applications across 11 frameworks and 7 languages, featuring realistic flaws such as injection vulnerabilities, authentication bypasses, and unsafe input handling. Using a Capture-the-Flag (CTF) setup, it tests CUAs' capacity to identify and exploit these weaknesses while navigating complex web interfaces. Evaluation of state-of-the-art CUAs reveals concerning trends: exploitation rates below 12% and low cybersecurity awareness. CUAs often fail at multi-step attack planning and misuse security tools. These results expose the current limitations of CUAs in web security contexts and highlight opportunities for developing more security-aware agents capable of effective vulnerability detection and exploitation.

cs.CR↗

arXiv2025

A Comparative Study of Android Performance Issues in Real-world Applications and Literature

Performance issues in Android applications significantly undermine users' experience, engagement, and retention, which is a long-lasting research topic in academia. Unlike functionality issues, performance issues are more difficult to diagnose and resolve due to their complex root causes, which often emerge only under specific conditions or payloads. Although many efforts haven attempt to mitigate the impact of performance issues by developing methods to automatically identify and resolve them, it remains unclear if this objective has been fulfilled, and the existing approaches indeed targeted on the most critical performance issues encountered in real-world settings. To this end, we conducted a large-scale comparative study of Android performance issues in real-world applications and literature. Specifically, we started by investigating real-world performance issues, their underlying root causes (i.e., contributing factors), and common code patterns. We then took an additional step to empirically summarize existing approaches and datasets through a literature review, assessing how well academic research reflects the real-world challenges faced by developers and users. Our comparison results show a substantial divergence exists in the primary performance concerns of researchers, developers, and users. Among all the identified factors, 57.14% have not been examined in academic research, while a substantial 76.39% remain unaddressed by existing tools, and 66.67% lack corresponding datasets. This stark contrast underscores a substantial gap in our understanding and management of performance issues. Consequently, it is crucial for our community to intensify efforts to bridge these gaps and achieve comprehensive detection and resolution of performance issues.

cs.SE↗

arXiv2025

Navigating the Labyrinth: Path-Sensitive Unit Test Generation with Large Language Models

Unit testing is essential for software quality assurance, yet writing and maintaining tests remains time-consuming and error-prone. To address this challenge, researchers have proposed various techniques for automating unit test generation, including traditional heuristic-based methods and more recent approaches that leverage large language models (LLMs). However, these existing approaches are inherently path-insensitive because they rely on fixed heuristics or limited contextual information and fail to reason about deep control-flow structures. As a result, they often struggle to achieve adequate coverage, particularly for deep or complex execution paths. In this work, we present a path-sensitive framework, JUnitGenie, to fill this gap by combining code knowledge with the semantic capabilities of LLMs in guiding context-aware unit test generation. After extracting code knowledge from Java projects, JUnitGenie distills this knowledge into structured prompts to guide the generation of high-coverage unit tests. We evaluate JUnitGenie on 2,258 complex focal methods from ten real-world Java projects. The results show that JUnitGenie generates valid tests and improves branch and line coverage by 29.60% and 31.00% on average over both heuristic and LLM-based baselines. We further demonstrate that the generated test cases can uncover real-world bugs, which were later confirmed and fixed by developers.

cs.SE↗

arXiv2025

Towards Context-aware Mobile Privacy Notice: Implementation of A Deployable Contextual Privacy Policies Generator

Lengthy and legally phrased privacy policies impede users' understanding of how mobile applications collect and process personal data. Prior work proposed Contextual Privacy Policies (CPPs) for mobile apps to display shorter policy snippets only in the corresponding user interface contexts, but the pipeline could not be deployable in real-world mobile environments. In this paper, we present PrivScan, the first deployable CPP Software Development Kit (SDK) for Android. It captures live app screenshots to identify GUI elements associated with types of personal data and displays CPPs in a concise, user-facing format. We provide a lightweight floating button that offers low-friction, on-demand control. The architecture leverages remote deployment to decouple the multimodal backend pipeline from a mobile client comprising five modular components, thereby reducing on-device resource demands and easing cross-platform portability. A feasibility-oriented evaluation shows an average execution time of 9.15\,s, demonstrating the practicality of our approach. The source code of PrivScan is available at https://github.com/buyanghc/PrivScan and the demo video can be found at https://www.youtube.com/watch?v=ck-25otfyHc.

cs.CR↗

arXiv2025

A Benchmark for Localizing Code and Non-Code Issues in Software Projects

Accurate project localization (e.g., files and functions) for issue resolution is a critical first step in software maintenance. However, existing benchmarks for issue localization, such as SWE-Bench and LocBench, are limited. They focus predominantly on pull-request issues and code locations, ignoring other evidence and non-code files such as commits, comments, configurations, and documentation. To address this gap, we introduce MULocBench, a comprehensive dataset of 1,100 issues from 46 popular GitHub Python projects. Comparing with existing benchmarks, MULocBench offers greater diversity in issue types, root causes, location scopes, and file types, providing a more realistic testbed for evaluation. Using this benchmark, we assess the performance of state-of-the-art localization methods and five LLM-based prompting strategies. Our results reveal significant limitations in current techniques: even at the file level, performance metrics (Acc@5, F1) remain below 40%. This underscores the challenge of generalizing to realistic, multi-faceted issue resolution. To enable future research on project localization for issue resolution, we publicly release MULocBench at https://huggingface.co/datasets/somethingone/MULocBench.

cs.SE↗

arXiv2025

Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol

Applications of Large Language Models~(LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions. Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance. This paper decomposes LLM applications into a three-layer architecture: \textbf{\textit{System Shell Layer}}, \textbf{\textit{Prompt Orchestration Layer}}, and \textbf{\textit{LLM Inference Core}}. We then assess the applicability of traditional software testing methods in each layer: directly applicable at the shell layer, requiring semantic reinterpretation at the orchestration layer, and necessitating paradigm shifts at the inference core. A comparative analysis of Testing AI methods from the software engineering community and safety analysis techniques from the AI community reveals structural disconnects in testing unit abstraction, evaluation metrics, and lifecycle management. We identify four fundamental differences that underlie 6 core challenges. To address these, we propose four types of collaborative strategies (\emph{Retain}, \emph{Translate}, \emph{Integrate}, and \emph{Runtime}) and explore a closed-loop, trustworthy quality assurance framework that combines pre-deployment validation with runtime monitoring. Based on these strategies, we offer practical guidance and a protocol proposal to support the standardization and tooling of LLM application testing. We propose a protocol \textbf{\textit{Agent Interaction Communication Language}} (AICL) that is used to communicate between AI agents. AICL has the test-oriented features and is easily integrated in the current agent framework.

cs.SE↗

arXiv2025

When Prompt Engineering Meets Software Engineering: CNL-P as Natural and Robust "APIs'' for Human-AI Interaction

With the growing capabilities of large language models (LLMs), they are increasingly applied in areas like intelligent customer service, code generation, and knowledge management. Natural language (NL) prompts act as the ``APIs'' for human-LLM interaction. To improve prompt quality, best practices for prompt engineering (PE) have been developed, including writing guidelines and templates. Building on this, we propose Controlled NL for Prompt (CNL-P), which not only incorporates PE best practices but also draws on key principles from software engineering (SE). CNL-P introduces precise grammar structures and strict semantic norms, further eliminating NL's ambiguity, allowing for a declarative but structured and accurate expression of user intent. This helps LLMs better interpret and execute the prompts, leading to more consistent and higher-quality outputs. We also introduce an NL2CNL-P conversion tool based on LLMs, enabling users to write prompts in NL, which are then transformed into CNL-P format, thus lowering the learning curve of CNL-P. In particular, we develop a linting tool that checks CNL-P prompts for syntactic and semantic accuracy, applying static analysis techniques to NL for the first time. Extensive experiments demonstrate that CNL-P enhances the quality of LLM responses through the novel and organic synergy of PE and SE. We believe that CNL-P can bridge the gap between emerging PE and traditional SE, laying the foundation for a new programming paradigm centered around NL.

cs.SE↗

arXiv2025

Think Like an Engineer: A Neuro-Symbolic Collaboration Agent for Generative Software Requirements Elicitation and Self-Review

The vision of End-User Software Engineering (EUSE) is to empower non-professional users with full control over the software development lifecycle. It aims to enable users to drive generative software development using only natural language requirements. However, since end-users often lack knowledge of software engineering, their requirement descriptions are frequently ambiguous, raising significant challenges to generative software development. Although existing approaches utilize structured languages like Gherkin to clarify user narratives, they still struggle to express the causal logic between preconditions and behavior actions. This paper introduces RequireCEG, a requirement elicitation and self-review agent that embeds causal-effect graphs (CEGs) in a neuro-symbolic collaboration architecture. RequireCEG first uses a feature tree to analyze user narratives hierarchically, clearly defining the scope of software components and their system behavior requirements. Next, it constructs the self-healing CEGs based on the elicited requirements, capturing the causal relationships between atomic preconditions and behavioral actions. Finally, the constructed CEGs are used to review and optimize Gherkin scenarios, ensuring consistency between the generated Gherkin requirements and the system behavior requirements elicited from user narratives. To evaluate our method, we created the RGPair benchmark dataset and conducted extensive experiments. It achieves an 87% coverage rate and raises diversity by 51.88%.

cs.SE↗

arXiv2025

Rethinking Broken Object Level Authorization Attacks Under Zero Trust Principle

RESTful APIs facilitate data exchange between applications, but they also expose sensitive resources to potential exploitation. Broken Object Level Authorization (BOLA) is the top vulnerability in the OWASP API Security Top 10, exemplifies a critical access control flaw where attackers manipulate API parameters to gain unauthorized access. To address this, we propose BOLAZ, a defense framework grounded in zero trust principles. BOLAZ analyzes the data flow of resource IDs, pinpointing BOLA attack injection points and determining the associated authorization intervals to prevent horizontal privilege escalation. Our approach leverages static taint tracking to categorize APIs into producers and consumers based on how they handle resource IDs. By mapping the propagation paths of resource IDs, BOLAZ captures the context in which these IDs are produced and consumed, allowing for precise identification of authorization boundaries. Unlike defense methods based on common authorization models, BOLAZ is the first authorization-guided method that adapts defense rules based on the system's best-practice authorization logic. We validate BOLAZ through empirical research on 10 GitHub projects. The results demonstrate BOLAZ's effectiveness in defending against vulnerabilities collected from CVE and discovering 35 new BOLA vulnerabilities in the wild, demonstrating its practicality in real-world deployments.

cs.CR↗

arXiv2025

LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements

Health, Safety, and Environment (HSE) compliance assessment demands dynamic real-time decision-making under complicated regulations and complex human-machine-environment interactions. While large language models (LLMs) hold significant potential for decision intelligence and contextual dialogue, their capacity for domain-specific knowledge in HSE and structured legal reasoning remains underexplored. We introduce HSE-Bench, the first benchmark dataset designed to evaluate the HSE compliance assessment capabilities of LLM. HSE-Bench comprises over 1,000 manually curated questions drawn from regulations, court cases, safety exams, and fieldwork videos, and integrates a reasoning flow based on Issue spotting, rule Recall, rule Application, and rule Conclusion (IRAC) to assess the holistic reasoning pipeline. We conduct extensive evaluations on different prompting strategies and more than 10 LLMs, including foundation models, reasoning models and multimodal vision models. The results show that, although current LLMs achieve good performance, their capabilities largely rely on semantic matching rather than principled reasoning grounded in the underlying HSE compliance context. Moreover, their native reasoning trace lacks the systematic legal reasoning required for rigorous HSE compliance assessment. To alleviate these, we propose a new prompting technique, Reasoning of Expert (RoE), which guides LLMs to simulate the reasoning process of different experts for compliance assessment and reach a more accurate unified decision. We hope our study highlights reasoning gaps in LLMs for HSE compliance and inspires further research on related tasks.

cs.CL↗

arXiv2025

Software Security Mapping Framework: Operationalization of Security Requirements

The escalating complexity of modern software development environments has heightened concerns around supply chain security. However, existing frameworks often fall short in translating abstract security principles into concrete, actionable practices. This paper introduces the Software Security Mapping Framework, a structured solution designed to operationalize security requirements across hierarchical levels -- from high-level regulatory standards (e.g., ISM, Australia cybersecurity standard published by the Australian Signals Directorate), through mid-level frameworks (e.g., NIST SSDF, the U.S. Secure Software Development Framework), to fine-grained technical activities (e.g., SLSA, a software supply chain security framework). Developed through collaborative research with academic experts and industry practitioners, the framework systematically maps 131 refined security requirements to over 400 actionable operational steps spanning the software development lifecycle. It is grounded in four core security goals: Secure Software Environment, Secure Software Development, Software Traceability, and Vulnerability Management. Our approach leverages the KAOS goal modeling methodology to establish traceable linkages between strategic goals and tactical operations, enhancing clarity, accountability, and practical implementation. To facilitate adoption, we provide a web-based navigation tool for interactive exploration of the framework. A real-world case study based on the Log4j vulnerability illustrates the framework's utility by generating a tailored checklist aligned with industry best practices. Additionally, we offer a structured, machine-readable OSCAL Catalog Model of the Software Security Mapping Framework, enabling organizations to automate implementation, streamline compliance processes, and respond effectively to evolving security risks.

cs.SE↗

arXiv2025

A Case Study of Scalable Content Annotation Using Multi-LLM Consensus and Human Review

Content annotation at scale remains challenging, requiring substantial human expertise and effort. This paper presents a case study in code documentation analysis, where we explore the balance between automation efficiency and annotation accuracy. We present MCHR (Multi-LLM Consensus with Human Review), a novel semi-automated framework that enhances annotation scalability through the systematic integration of multiple LLMs and targeted human review. Our framework introduces a structured consensus-building mechanism among LLMs and an adaptive review protocol that strategically engages human expertise. Through our case study, we demonstrate that MCHR reduces annotation time by 32% to 100% compared to manual annotation while maintaining high accuracy (85.5% to 98%) across different difficulty levels, from basic binary classification to challenging open-set scenarios.

cs.HC↗

arXiv2025

LogiAgent: Automated Logical Testing for REST Systems with LLM-Based Multi-Agents

Automated testing for REST APIs has become essential for ensuring the correctness and reliability of modern web services. While existing approaches primarily focus on detecting server crashes and error codes, they often overlook logical issues that arise due to evolving business logic and domain-specific requirements. To address this limitation, we propose LogiAgent, a novel approach for logical testing of REST systems. Built upon a large language model (LLM)-driven multi-agent framework, LogiAgent integrates a Test Scenario Generator, API Request Executor, and API Response Validator to collaboratively generate, execute, and validate API test scenarios. Unlike traditional testing methods that focus on status codes like 5xx, LogiAgent incorporates logical oracles that assess responses based on business logic, ensuring more comprehensive testing. The system is further enhanced by an Execution Memory component that stores historical API execution data for contextual consistency. We conduct extensive experiments across 12 real-world REST systems, demonstrating that LogiAgent effectively identifies 234 logical issues with an accuracy of 66.19%. Additionally, it basically excels in detecting server crashes and achieves superior test coverage compared to four state-of-the-art REST API testing tools. An ablation study confirms the significant contribution of LogiAgent's memory components to improving test coverage.

cs.SE↗

arXiv2025

SeeAction: Towards Reverse Engineering How-What-Where of HCI Actions from Screencasts for UI Automation

UI automation is a useful technique for UI testing, bug reproduction, and robotic process automation. Recording user actions with an application assists rapid development of UI automation scripts, but existing recording techniques are intrusive, rely on OS or GUI framework accessibility support, or assume specific app implementations. Reverse engineering user actions from screencasts is non-intrusive, but a key reverse-engineering step is currently missing - recognizing human-understandable structured user actions ([command] [widget] [location]) from action screencasts. To fill the gap, we propose a deep learning-based computer vision model that can recognize 11 commands and 11 widgets, and generate location phrases from action screencasts, through joint learning and multi-task learning. We label a large dataset with 7260 video-action pairs, which record user interactions with Word, Zoom, Firefox, Photoshop, and Windows 10 Settings. Through extensive experiments, we confirm the effectiveness and generality of our model, and demonstrate the usefulness of a screencast-to-action-script tool built upon our model for bug reproduction.

cs.SE↗

arXiv2025

Privacy Bills of Materials: A Transparent Privacy Information Inventory for Collaborative Privacy Notice Generation in Mobile App Development

Privacy regulations mandate that developers must provide authentic and comprehensive privacy notices, e.g., privacy policies or labels, to inform users of their apps' privacy practices. However, due to a lack of knowledge of privacy requirements, developers often struggle to create accurate privacy notices, especially for sophisticated mobile apps with complex features and in crowded development teams. To address these challenges, we introduce Privacy Bills of Materials (PriBOM), a systematic software engineering approach that leverages different development team roles to better capture and coordinate mobile app privacy information. PriBOM facilitates transparency-centric privacy documentation and specific privacy notice creation, enabling traceability and trackability of privacy practices. We present a pre-fill of PriBOM based on static analysis and privacy notice analysis techniques. We demonstrate the perceived usefulness of PriBOM through a human evaluation with 150 diverse participants. Our findings suggest that PriBOM could serve as a significant solution for providing privacy support in DevOps for mobile apps.

cs.CR↗

arXiv2025

From Code to Courtroom: LLMs as the New Software Judges

Recently, Large Language Models (LLMs) have been increasingly used to automate SE tasks such as code generation and summarization. However, evaluating the quality of LLM-generated software artifacts remains challenging. Human evaluation, while effective, is very costly and time-consuming. Traditional automated metrics like BLEU rely on high-quality references and struggle to capture nuanced aspects of software quality, such as readability and usefulness. In response, the LLM-as-a-Judge paradigm, which employs LLMs for automated evaluation, has emerged. Given that LLMs are typically trained to align with human judgment and possess strong coding abilities and reasoning skills, they hold promise as cost-effective and scalable surrogates for human evaluators. Nevertheless, LLM-as-a-Judge research in the SE community is still in its early stages, with many breakthroughs needed. This forward-looking SE 2030 paper aims to steer the research community toward advancing LLM-as-a-Judge for evaluating LLMgenerated software artifacts, while also sharing potential research paths to achieve this goal. We provide a literature review of existing SE studies on LLM-as-a-Judge and envision these frameworks as reliable, robust, and scalable human surrogates capable of evaluating software artifacts with consistent, multi-faceted assessments by 2030 and beyond. To validate this vision, we analyze the limitations of current studies, identify key research gaps, and outline a detailed roadmap to guide future developments of LLM-as-a-Judge in software engineering. While not intended to be a definitive guide, our work aims to foster further research and adoption of LLM-as-a-Judge frameworks within the SE community, ultimately improving the effectiveness and scalability of software artifact evaluation methods.

cs.SE↗