arXiv subjects

Ying Zou

Publications and source records attributed to Ying Zou.

At least 19 recordsLinked to original sources

arXiv2026

LabelMate: An LLM-Driven Framework for Refined Issue Report Labeling

Software users often submit issue reports to a product's issue tracking system to report defects, suggest enhancements, or raise other product-related concerns. Labeling these issue reports supports effective planning and improves community engagement. However, many issue reports remain unlabeled due to the substantial manual effort required to design an appropriate label taxonomy, then assign suitable labels from this taxonomy to new issue reports. Existing automated labeling approaches attempt to mitigate these challenges. However, they suffer from key limitations, such as extensive manual intervention, the assignment of generic labels, and a dependence on existing labeled datasets. To address these limitations, we propose LabelMate, a novel Large Language Model (LLM)-driven framework that (1) derives a comprehensive, project-specific label set from historical issue reports and (2) automatically assigns relevant labels to new issue reports without requiring any pre-labeled training data. We evaluate LabelMate on 16,500 issue reports from 30 popular and diverse GitHub repositories. Based on this dataset, our approach generates a coherent list of 275 labels and achieves an average labeling accuracy of 89.84%, a statistically significant improvement over existing generic label assigning approaches. These results demonstrate that LabelMate offers an efficient, domain-adaptive solution to streamline the issue labeling process.

cs.SE↗

arXiv2026

RefactorAssist: Agentic Refinement for Reliable Code Refactoring

Code refactoring aims to enhance the internal structure of source code without affecting its functional behavior. The recent advancements of Large Language Models (LLMs) have demonstrated potential for automating software engineering tasks, such as code refactoring. However, the refactorings produced by LLMs often introduce subtle errors, leading to functional behavior changes and failed unit tests, which limit their practical adoption. To address the limitations of LLM-generated refactorings, we analyze the root causes of their failures and develop the RefactorAssist agent to improve the functional correctness of LLM-generated refactorings. To this end, we use 10 open-source Java projects with their native test suites and manually evaluate why LLM-generated refactorings fail unit tests. We then design an agentic approach that leverages unit-test logs, error explanations, project context retrieval, and code diffs to guide the iterative refactoring. Our findings show that the main reasons for failure are context misunderstanding/hallucination (24.3%), incorrect or inconsistent renaming (15.3%), adding new functionality or variables (13.7%), code incompleteness (11.3%), syntax and structural errors (9.7%), edge cases not handled (9%), improper type handling (8.7%), and variables outside scope (8%). To make our approach cost-effective, RefactorAssist first applies a static repair step for missing imports, unbalanced brackets, and compilation errors without LLMs. For remaining failures, RefactorAssist incorporates error logs and code diffs, achieving up to a 70.8% repair rate on the remaining failures and a 94.2% cumulative pass rate under the best-performing configuration. These results indicate that static checks and test-guided, context-aware agentic repair can increase the reliability of LLM-generated refactorings, bringing them closer to practical integration within developer workflows.

cs.SE↗

arXiv2026

From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality

Code review helps maintain software quality before code integration, but it also imposes a substantial workload on human reviewers. As generative artificial intelligence becomes part of software development, code review is shifting from a primarily human review process toward AI-supported review processes in which large language model (LLM) reviewers and AI agent reviewers participate alongside human reviewers. However, we still lack empirical evidence on how this transition affects review efficiency and review quality. In this paper, we study 1.02 million reviewed pull requests from 207 GitHub projects that transition across three code review eras: human-centric review, LLM-assisted review, and agentic code review. We identify three AI reviewer adoption practices: Gradual AI Adoption, Rapid LLM Adoption, and Rapid AI Agent Adoption. We further model pull request review discussions as reviewer interaction sequences to characterize how human, LLM, and AI agent reviewers collaborate during the review process. Our results show that agent-involved collaboration patterns, especially reviews initiated by AI agents or involving multiple AI agents, are associated with faster review decisions under Gradual AI Adoption and Rapid AI Agent Adoption. However, these efficiency gains do not translate into better review quality. We also find that review activity and pull request type remain important across eras, while human-AI collaboration patterns become the strongest explanatory factor for review efficiency once LLM and AI agent reviewers participate. These findings provide empirical guidance for designing AI-supported code review processes that improve efficiency without weakening review quality.

cs.SE↗

arXiv2026

Human-AI Synergy in Agentic Code Review

Code review is a critical software engineering practice where developers review code changes before integration to ensure code quality, detect defects, and improve maintainability. In recent years, AI agents that can understand code context, plan review actions, and interact with development environments have been increasingly integrated into the code review process. However, there is limited empirical evidence to compare the effectiveness of AI agents and human reviewers in collaborative workflows. To address this gap, we conduct a large-scale empirical analysis of 278,790 code review conversations across 300 open-source GitHub projects. In our study, we aim to compare the feedback differences provided by human reviewers and AI agents. We investigate human-AI collaboration patterns in review conversations to understand how interaction shapes review outcomes. Moreover, we analyze the adoption of code suggestions provided by human reviewers and AI agents into the codebase and how adopted suggestions change code quality. We find that human reviewers provide additional feedback than AI agents, including understanding, testing, and knowledge transfer. Human reviewers exchange 11.8% more rounds when reviewing AI-generated code than human-written code. Moreover, code suggestions made by AI agents are adopted into the codebase at a significantly lower rate than suggestions proposed by human reviewers. Over half of unadopted suggestions from AI agents are either incorrect or addressed through alternative fixes by developers. When adopted, suggestions provided by AI agents produce significantly larger increases in code complexity and code size than suggestions provided by human reviewers. Our findings suggest that while AI agents can scale defect screening, human oversight remains critical for ensuring suggestion quality and providing contextual feedback that AI agents lack.

cs.SE↗

arXiv2026

The Promise and Reality of Continuous Integration Caching: An Empirical Study of Travis CI Builds

Continuous Integration (CI) provides early feedback by automatically building software, but long build durations can hinder developer productivity. CI services use caching to speed up builds by reusing infrequently changing artifacts, yet little is known about how caching is adopted in practice and what challenges it entails. In this paper, we conduct a large-scale empirical study of CI caching in Travis CI, analyzing 513,384 builds from 1,279 GitHub projects. We find that only 30% of projects adopt CI caching, and early adopters are typically more mature, with more dependencies, commits, and longer CI lifespans. To understand non-adoption, we submit pull requests enabling caching in non-adopting projects, and nearly half are accepted or merged. Developer feedback indicates that non- or late adoption mainly results from limited awareness of CI caching support. We further study cache maintenance and identify five common activities, performed by 24% of cache-enabled projects. While one-third of projects see substantial build-time reductions, cache uploads occur in 97% of builds, and 27% of projects contain stale cached artifacts. An analysis of reported caching issues shows developers mainly struggle with corrupted or outdated caches and request broader caching features. Overall, CI caching does not benefit all projects, requires ongoing maintenance, and is more complex in practice than many developers expect.

cs.SE↗

arXiv2026

An Empirical Analysis of Community and Coding Patterns in OSS4SG vs. Conventional OSS

Open Source Software for Social Good (OSS4SG) projects aim to address critical societal challenges, such as healthcare access and community safety. Understanding the community dynamics and contributor patterns in these projects is essential for ensuring their sustainability and long-term impact. However, while extensive research has focused on conventional Open Source Software (OSS), little is known about how the mission-driven nature of OSS4SG influences its development practices. To address this gap, we conduct a large-scale empirical study of 1,039 GitHub repositories, comprising 422 OSS4SG and 617 conventional OSS projects, to compare community structure, contributor engagement, and coding practices. Our findings reveal that OSS4SG projects foster significantly more stable and "sticky" (63.4%) communities, whereas conventional OSS projects are more "magnetic" (75.4%), attracting a high turnover of contributors. OSS4SG projects also demonstrate consistent engagement throughout the year, while conventional OSS communities exhibit seasonal fluctuations. Additionally, OSS4SG projects rely heavily on core contributors for both code quality and issue resolution, while conventional OSS projects leverage casual contributors for issue resolution, with core contributors focusing primarily on code quality.

cs.SE↗

arXiv2025

Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality

Large Language Models (LLMs) are increasingly used by developers for conversational coding assistance, including code generation, technical questions, and iterative problem solving. However, limited empirical evidence exists on the topics developers discuss with LLMs, how interaction patterns vary across tasks, and how the quality of generated code changes across conversational turns. To address this, we construct CodeChat, a large-scale dataset derived from WildChat. CodeChat contains 587,568 real-world developer-LLM conversations and 1.7 million code snippets across more than 20 programming languages. We identify the topics developers raise and examine how their engagement varies across topics. We then assess the quality of generated code across five programming languages (i.e., Python, JavaScript, C++, Java, and C#) and analyze how quality issues evolve across conversational turns. We find that developers most frequently seek help with web design (9.6% of conversations) and machine learning (8.7%), and that conversations often grow long because developers repeatedly shift use cases. LLM-generated code exhibits prevalent, language-specific issues whose prevalence does not consistently decrease in interactions lasting at least five turns. Among successful syntax-error resolutions, prompts that explicitly identify the error and request a fix are the most frequently observed. Our findings suggest that conversational assistants should track evolving developer intent and monitor code quality across turns.

cs.SE↗

arXiv2025

MemoCoder: Automated Function Synthesis using LLM-Supported Agents

With the widespread adoption of Large Language Models (LLMs) such as GitHub Copilot and ChatGPT, developers increasingly rely on AI-assisted tools to support code generation. While LLMs can generate syntactically correct solutions for well-structured programming tasks, they often struggle with challenges that require iterative debugging, error handling, or adaptation to diverse problem structures. Existing approaches such as fine-tuning or self-repair strategies either require costly retraining or lack mechanisms to accumulate and reuse knowledge from previous attempts. To address these limitations, we propose MemoCoder, a multi-agent framework that enables collaborative problem solving and persistent learning from past fixes. At the core of MemoCoder is a Fixing Knowledge Set, which stores successful repairs and supports retrieval for future tasks. A central Mentor Agent supervises the repair process by identifying recurring error patterns and refining high-level fixing strategies, providing a novel supervisory role that guides the self-repair loop. We evaluate MemoCoder across three public benchmarks -- MBPP, HumanEval, and LiveCodeBench -- spanning a range of problem complexities. Experimental results show that MemoCoder consistently outperforms both zero-shot prompting and a Self-Repair strategy, with improvements ranging from 3.1% to 12.1% in Pass@10 and from 1.4% to 14.5% in Pass@50, demonstrating its effectiveness in iterative refinement and knowledge-guided code generation.

cs.SE↗

arXiv2025

Never Come Up Empty: Adaptive HyDE Retrieval for Improving LLM Developer Support

Large Language Models (LLMs) have shown promise in assisting developers with code-related questions; however, LLMs carry the risk of generating unreliable answers. To address this, Retrieval-Augmented Generation (RAG) has been proposed to reduce the unreliability (i.e., hallucinations) of LLMs. However, designing effective pipelines remains challenging due to numerous design choices. In this paper, we construct a retrieval corpus of over 3 million Java and Python related Stack Overflow posts with accepted answers, and explore various RAG pipeline designs to answer developer questions, evaluating their effectiveness in generating accurate and reliable responses. More specifically, we (1) design and evaluate 7 different RAG pipelines and 63 pipeline variants to answer questions that have historically similar matches, and (2) address new questions without any close prior matches by automatically lowering the similarity threshold during retrieval, thereby increasing the chance of finding partially relevant context and improving coverage for unseen cases. We find that implementing a RAG pipeline combining hypothetical-documentation-embedding (HyDE) with the full-answer context performs best in retrieving and answering similarcontent for Stack Overflow questions. Finally, we apply our optimal RAG pipeline to 4 open-source LLMs and compare the results to their zero-shot performance. Our findings show that RAG with our optimal RAG pipeline consistently outperforms zero-shot baselines across models, achieving higher scores for helpfulness, correctness, and detail with LLM-as-a-judge. These findings demonstrate that our optimal RAG pipelines robustly enhance answer quality for a wide range of developer queries including both previously seen and novel questions across different LLMs

cs.SE↗

arXiv2025

Enhancing COBOL Code Explanations: A Multi-Agents Approach Using Large Language Models

Common Business Oriented Language (COBOL) is a programming language used to develop business applications that are widely adopted by financial, business, and government agencies. Due to its age, complexity, and declining number of COBOL developers, maintaining COBOL codebases is becoming increasingly challenging. In particular, the lack of documentation makes it difficult for new developers to effectively understand and maintain COBOL systems. Existing research utilizes large language models (LLMs) to explain the functionality of code snippets. However, COBOL presents unique challenges due to its architectural and syntactical differences, which often cause its code to exceed the token window size of LLMs. In this work, we propose a multi-agent approach that leverages two LLM-based agents working collaboratively to generate explanations for functions, files, and the overall project. These agents incorporate together by utilizing contextual information from the codebase into the code explanation prompts. We evaluate the effectiveness of our approach using 14 open-source, real-world COBOL projects. Our results indicate that our approach performs significantly better than the baseline in function code explanation, with improvements of 12.67%, 18.59%, and 0.62% in terms of METEOR, chrF, and SentenceBERT scores, respectively. At the file level, our approach effectively explains both short and long COBOL files that exceed the token window size of LLMs and surpass the baseline by 4.21%, 10.72%, and 14.68% in explaining the purpose, functionality, and clarity of the generated explanation. At the project level, our approach generates explanations that convey the functionality and purpose of 82% of the selected projects.

cs.SE↗

arXiv2025

Planar Collisionless Shock Simulations with Semi-Implicit Particle-in-Cell Model FLEKS

This study investigates the applicability of the semi-implicit particle-in-cell code FLEKS to heliospheric shock simulations. We examine one- and two-dimensional local planar shock simulations, initialized using MHD states with upstream conditions representative of plasmas in the hypersonic, $\beta\sim 1$ regime, for both quasi-perpendicular and quasi-parallel configurations. The refined algorithm in FLEKS proves robust, enabling accurate shock simulations with a grid resolution on the order of the electron inertial length $d_e$. Our simulations successfully capture key shock features, including shock structures (foot, ramp, overshoot, and undershoot), upstream and downstream waves (fast magnetosonic, whistler, Alfv\'en ion-cyclotron, and mirror modes), and non-Maxwellian particle distributions. Crucially, we find that at least two spatial dimensions are critical for accurately reproducing downstream wave physics in quasi-perpendicular shocks and capturing the complex dynamics of quasi-parallel shocks, including surface rippling, shocklets, SLAMS, magnetic reconnection and jets. Furthermore, our parameter studies demonstrate the impact of mass ratio and grid resolution on shock physics. This work provides valuable guidance for selecting appropriate physical and numerical parameters for shock simulations using a semi-implicit PIC method, paving the way for incorporating kinetic shock processes into large-scale collisionless plasma simulations with the MHD-AEPIC model.

physics.space-ph↗

arXiv2025

Towards Refining Developer Questions using LLM-Based Named Entity Recognition for Developer Chatroom Conversations

In software engineering chatrooms, communication is often hindered by imprecise questions that cannot be answered. Recognizing key entities can be essential for improving question clarity and facilitating better exchange. However, existing research using natural language processing techniques often overlooks these software-specific nuances. In this paper, we introduce Software-specific Named Entity Recognition, Intent Detection, and Resolution Classification (SENIR), a labeling approach that leverages a Large Language Model to annotate entities, intents, and resolution status in developer chatroom conversations. To offer quantitative guidance for improving question clarity and resolvability, we build a resolution prediction model that leverages SENIR's entity and intent labels along with additional predictive features. We evaluate SENIR on the DISCO dataset using a subset of annotated chatroom dialogues. SENIR achieves an 86% F-score for entity recognition, a 71% F-score for intent detection, and an 89% F-score for resolution status classification. Furthermore, our resolution prediction model, tested with various sampling strategies (random undersampling and oversampling with SMOTE) and evaluation methods (5-fold cross-validation, 10-fold cross-validation, and bootstrapping), demonstrates AUC values ranging from 0.7 to 0.8. Key factors influencing resolution include positive sentiment and entities such as Programming Language and User Variable across multiple intents, while diagnostic entities are more relevant in error-related questions. Moreover, resolution rates vary significantly by intent: questions about API Usage and API Change achieve higher resolution rates, whereas Discrepancy and Review have lower resolution rates. A Chi-Square analysis confirms the statistical significance of these differences.

cs.SE↗

arXiv2024

Enhancing Software Maintenance: A Learning to Rank Approach for Co-changed Method Identification

With the increasing complexity of large-scale software systems, identifying all necessary modifications for a specific change is challenging. Co-changed methods, which are methods frequently modified together, are crucial for understanding software dependencies. However, existing methods often produce large results with high false positives. Focusing on pull requests instead of individual commits provides a more comprehensive view of related changes, capturing essential co-change relationships. To address these challenges, we propose a learning-to-rank approach that combines source code features and change history to predict and rank co-changed methods at the pull-request level. Experiments on 150 open-source Java projects, totaling 41.5 million lines of code and 634,216 pull requests, show that the Random Forest model outperforms other models by 2.5 to 12.8 percent in NDCG@5. It also surpasses baselines such as file proximity, code clones, FCP2Vec, and StarCoder 2 by 4.7 to 537.5 percent. Models trained on longer historical data (90 to 180 days) perform consistently, while accuracy declines after 60 days, highlighting the need for bi-monthly retraining. This approach provides an effective tool for managing co-changed methods, enabling development teams to handle dependencies and maintain software quality.

cs.SE↗

arXiv2024

An Empirical Study on the Code Refactoring Capability of Large Language Models

Large Language Models (LLMs) have shown potential to enhance software development through automated code generation and refactoring, reducing development time and improving code quality. This study empirically evaluates StarCoder2, an LLM optimized for code generation, in refactoring code across 30 open-source Java projects. We compare StarCoder2's performance against human developers, focusing on (1) code quality improvements, (2) types and effectiveness of refactorings, and (3) enhancements through one-shot and chain-of-thought prompting. Our results indicate that StarCoder2 reduces code smells by 20.1% more than developers, excelling in systematic issues like Long Statement and Magic Number, while developers handle complex, context-dependent issues better. One-shot prompting increases the unit test pass rate by 6.15% and improves code smell reduction by 3.52%. Generating five refactorings per input further increases the pass rate by 28.8%, suggesting that combining one-shot prompting with multiple refactorings optimizes performance. These findings provide insights into StarCoder2's potential and best practices for integrating LLMs into software refactoring, supporting more efficient and effective code improvement in real-world applications.

cs.SE↗

arXiv2024

Energy-Efficient Software Development: A Multi-dimensional Empirical Analysis of Stack Overflow

Energy consumption of software applications has emerged as a critical concern for developers to contemplate in their daily development processes. Previous studies have surveyed a limited number of developers to understand their viewpoints on energy consumption. We complement these studies by analyzing a meticulously curated dataset of 1,193 Stack Overflow (SO) questions concerning energy consumption. These questions capture real-world energy-related challenges in practice. To understand practitioners' perceptions, we investigate the intentions behind these questions, semantic topics, and associated technologies (e.g., programming languages). Our results reveal that: (i) the most prevalent energy consumption topic is about balancing Positioning usage; (ii) efficiently handling data is particularly challenging, with these questions having the longest response times; (iii) practitioners primarily ask questions to understand a concept or API related to energy consumption; and (iv) practitioners are concerned about energy consumption across multiple levels-hardware, operating systems, and programming languages-during energy efficient software development. Our findings raise awareness about energy consumption's impact on software development. We also derive actionable implications for energy optimization at different levels (e.g., optimizing API usage or hardware accesses) during energy-aware software development.

cs.SE↗

arXiv2024

LLM-Cure: LLM-based Competitor User Review Analysis for Feature Enhancement

The exponential growth of the mobile app market underscores the importance of constant innovation and rapid response to user demands. As user satisfaction is paramount to the success of a mobile application (app), developers typically rely on user reviews, which represent user feedback that includes ratings and comments to identify areas for improvement. However, the sheer volume of user reviews poses challenges in manual analysis, necessitating automated approaches. Existing automated approaches either analyze only the target apps reviews, neglecting the comparison of similar features to competitors or fail to provide suggestions for feature enhancement. To address these gaps, we propose a Large Language Model (LLM)-based Competitive User Review Analysis for Feature Enhancement) (LLM-Cure), an approach powered by LLMs to automatically generate suggestion s for mobile app feature improvements. More specifically, LLM-Cure identifies and categorizes features within reviews by applying LLMs. When provided with a complaint in a user review, LLM-Cure curates highly rated (4 and 5 stars) reviews in competing apps related to the complaint and proposes potential improvements tailored to the target application. We evaluate LLM-Cure on 1,056,739 reviews of 70 popular Android apps. Our evaluation demonstrates that LLM-Cure significantly outperforms the state-of-the-art approaches in assigning features to reviews by up to 13% in F1-score, up to 16% in recall and up to 11% in precision. Additionally, LLM-Cure demonstrates its capability to provide suggestions for resolving user complaints. We verify the suggestions using the release notes that reflect the changes of features in the target mobile app. LLM-Cure achieves a promising average of 73% of the implementation of the provided suggestions.

cs.SE↗

arXiv2024

Magnetospheric control of ionospheric TEC perturbations via whistler-mode and ULF waves

The weakly ionized plasma in the Earth's ionosphere is controlled by a complex interplay between solar and magnetospheric inputs from above, atmospheric processes from below, and plasma electrodynamics from within. This interaction results in ionosphere structuring and variability that pose major challenges for accurate ionosphere prediction for global navigation satellite system (GNSS) related applications and space weather research. The ionospheric structuring and variability are often probed using the total electron content (TEC) and its relative perturbations (dTEC). Among dTEC variations observed at high latitudes, a unique modulation pattern has been linked to magnetospheric ultra low frequency (ULF) waves, yet its underlying mechanisms remain unclear. Here using magnetically-conjugate observations from the THEMIS spacecraft and a ground-based GPS receiver at Fairbanks, Alaska, we provide direct evidence that these dTEC modulations are driven by magnetospheric electron precipitation induced by ULF-modulated whistler-mode waves. We observed peak-to-peak dTEC amplitudes reaching ~0.5 TECU (1 TECU is equal to 10$^6$ electrons/m$^2$) with modulations spanning scales of ~5--100 km. The cross-correlation between our modeled and observed dTEC reached ~0.8 during the conjugacy period but decreased outside of it. The spectra of whistler-mode waves and dTEC also matched closely at ULF frequencies during the conjugacy period but diverged outside of it. Our findings elucidate the high-latitude dTEC generation from magnetospheric wave-induced precipitation, addressing a significant gap in current physics-based dTEC modeling. Theses results thus improve ionospheric dTEC prediction and enhance our understanding of magnetosphere-ionosphere coupling via ULF waves.

physics.space-ph↗

arXiv2024

Understanding Open Source Contributor Profiles in Popular Machine Learning Libraries

With the increasing popularity of machine learning (ML), many open-source software (OSS) contributors are attracted to developing and adopting ML approaches. Comprehensive understanding of ML contributors is crucial for successful ML OSS development and maintenance. Without such knowledge, there is a risk of inefficient resource allocation and hindered collaboration in ML OSS projects. Existing research focuses on understanding the difficulties and challenges perceived by ML contributors by user surveys. There is a lack of understanding of ML contributors based on their activities tracked from software repositories. In this paper, we aim to understand ML contributors by identifying contributor profiles in ML libraries. We further study contributors' OSS engagement from three aspects: workload composition, work preferences, and technical importance. By investigating 7,640 contributors from 6 popular ML libraries (TensorFlow, PyTorch, Keras, MXNet, Theano, and ONNX), we identify four contributor profiles: Core-Afterhour, Core-Workhour, Peripheral-Afterhour, and Peripheral-Workhour. We find that: 1) project experience, authored files, collaborations, and geographical location are significant features of all profiles; 2) contributors in Core profiles exhibit significantly different OSS engagement compared to Peripheral profiles; 3) contributors' work preferences and workload compositions significantly impact project popularity; 4) long-term contributors evolve towards making fewer, constant, balanced and less technical contributions.

cs.SE↗