arXiv subjects

Qiong Feng

Publications and source records attributed to Qiong Feng.

16 recordsLinked to original sources

arXiv2026

CrossLangFuzzer: Differential Testing of Cross-Language JVM Compilers

Modern JVM software increasingly integrates multiple programming languages, such as Java, Kotlin, Groovy, and Scala, within a single application. Supporting such interoperability requires JVM compilers to perform cross-language compilation while reconciling subtle semantic differences across language boundaries. Errors in this process can lead to critical miscompilations, yet existing compiler testing techniques focus exclusively on isolated, singlelanguage compilation. To address this gap, we present CrossLangFuzzer, the first differential testing framework for cross-language JVM compilation. CrossLangFuzzer leverages the Kotlin compiler's unified intermediate representation (IR) to synthesize cross-language test programs. It further applies seven mutation operators to diversify generated test programs and improve bug-finding capability. Evaluated on the latest versions of five major JVM compilers, CrossLangFuzzer uncovered 32 confirmed bugs, including 15 in Kotlin, 4 in Groovy, 7 in Scala 3, 2 in Scala 2, and 4 in Java. CrossLangFuzzer is open-source at https://github.com/XYZboom/CrossLangFuzzer

cs.SE↗

arXiv2026

CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation

Natural language to repository generation (NL2Repo) requires a system to construct an entire software repository from a natural-language requirements document. Compared with function-level code generation, this task demands longer planning horizons, stable interfaces across files, and iterative debugging of cross-file inconsistencies. To address these challenges, we propose CodeTeam, an LLM-based multi-agent framework that separates planning, decision making, and implementation into distinct, coordinated stages. In the planning stage, multiple Architect agents draft competing software design sketches (SDS), optionally grounded by retrieved design references. A CTO agent then evaluates, selects, and normalizes the most promising SDS into a machine-checkable contract that specifies file ownership, public interfaces, and dependency constraints. In the implementation stage, Developer agents generate code under a dependency-aware scheduler with bounded context and lightweight Git-based coordination, while a QA agent runs tests and drives iterative repairs. On the synthesis-based SketchEval benchmark, we explicitly compare CodeTeam's prompt-engineering (PE) and supervised fine-tuning (SFT) variants with the corresponding CodeS variants, where CodeTeam improves the overall SketchBLEU by 4.1 and 2.9 absolute points, respectively. On the execution-based NL2Repo-Bench benchmark, used as an external validation protocol, CodeTeam achieves the highest average test pass rate in both settings (34.6% PE, 42.3% SFT), confirming that the sketch-improvements extend to functional correctness under upstream test suites. Ablation results show that project-specific developer allocation and retrieval-augmented planning each contribute substantially to the SketchBLEU improvement (9.9% and 8.1% relative, respectively). CodeTeam and the experimental results are available at https://github.com/WhitenWhiten/CodeTeam

cs.SE↗

arXiv2026

DRReduce: Enhancing Syntax-Guided Program Reduction with Dependency Reconstruction

Program reduction is a technique for simplifying large, failure-inducing programs into minimal reproducible test cases. Language-specific tools such as CReduce achieve strong performance by leveraging deep semantic knowledge of C/C++, but are tightly coupled to a single language family. Language-agnostic reducers such as Perses address this by applying syntax-guided search across any grammar, yet share a fundamental limitation: deleting a node or subtree in isolation often breaks semantic coherence causing the property checker to reject the deletion and forcing the reducer to backtrack, limiting overall reduction effectiveness and efficiency. In this paper, we propose DRReduce, a framework that bridges this gap by augmenting language-agnostic syntactic reduction with a lightweight semantic layer: dependency reconstruction, which repairs program dependencies broken by a deletion in order to preserve the semantic validity of intermediate programs and increase the acceptance rate of the property checker. DRReduce constructs a semantic dependency graph from the input program, performs semantically coherent deletions with dependency reconstruction, and delegates further minimization to a syntax-guided reducer. We implement DRReduce for C and Java and evaluate it on real-world bug-triggering programs. Compared to SOTA syntax-guided reducers, DRReduce achieves average size reductions of 51.9%, 14.9%, and 19.8% over Perses, WDD, and CDD respectively, while completing reduction faster on the majority of programs. Compared to language-specific tools, DRReduce achieves results comparable to CReduce and Latra without any language-specific transformation rules, at 3.3x and 1.2x higher efficiency than CReduce and Latra on average, respectively. An ablation study confirms that dependency reconstruction reduces query invocations by 80.2%, reduction time by 58.7%, and final token count by over 55.1%.

cs.SE↗

arXiv2026

Using LLMs in Software Design: An Empirical Study of GitHub and A Practitioner Survey

Recent advancements in Large Language Models (LLMs) have demonstrated significant potential across a wide range of software engineering tasks, including software design, an area traditionally regarded as highly dependent on human expertise and judgment. However, there has been little research focusing on how LLMs are used in software design, nor on the associated benefits and drawbacks. This paper aims to bridge this gap by empirically investigating how software developers utilize LLMs in the context of software design. We conduct a mixed-methods study, combining a mining study of 291 developer-ChatGPT conversations shared on GitHub with a survey of 65 software practitioners. Our findings reveal nine distinct categories of design tasks supported by ChatGPT, including architecture design, data model design, and the use of design patterns. We further characterize developer-ChatGPT interactions, showing that developers primarily use ChatGPT for knowledge acquisition and design-related code generation, with most tasks situated at the detailed design level. The study identifies seven key benefits of utilizing LLMs in software design as perceived by developers, such as better technology selection and the early detection of design flaws. We also uncover six limitations, including the generation of overly lengthy and difficult-to-read outputs, the creation of inexecutable or incorrect code, and a heavy reliance on context that can lead to hallucinated results. These findings provide an evidence-based characterization of current LLM use in software design from both open-source and practitioner perspectives, highlighting a tension between perceived benefits and limitations, which lays a foundation for future research and the development of effective techniques and tools to integrate LLMs into software design practices.

cs.SE↗

arXiv2026

Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects

New generation of AI coding tools, including AI-powered IDEs equipped with agentic capabilities, can generate code within the context of the project. These AI IDEs are increasingly perceived as capable of producing project-level code at scale. However, there is limited empirical evidence on the extent to which they can generate large-scale software systems and what design issues such systems may exhibit. To address this gap, we conducted a study to explore the capability of Cursor in generating large-scale projects and to evaluate the design quality of projects generated by Cursor. First, we propose a Feature-Driven Human-In-The-Loop (FD-HITL) framework that systematically guides project generation from curated project descriptions. We generated 10 projects using Cursor with the FD-HITL framework across three application domains and multiple technologies. We assessed the functional correctness of these projects through manual evaluation, obtaining an average functional correctness score of 91%. Next, we analyzed the generated projects using two static analysis tools, CodeScene and SonarQube, to detect design issues. We identified 1,305 design issues categorized into 9 categories by CodeScene and 3,193 issues in 11 categories by SonarQube. Our findings show that (1) when used with the FD-HITL framework, Cursor can generate functional large-scale projects averaging 16,965 LoC and 114 files; (2) the generated projects nevertheless contain design issues that may pose long-term maintainability and evolvability risks, requiring careful review by experienced developers; (3) the most prevalent issues include Code Duplication, high Code Complexity, Large Methods, Framework Best-Practice Violations, Exception-Handling Issues and Accessibility Issues; (4) these design issues violate design principles such as SRP, SoC, and DRY. The replication package is at https://github.com/Kashifraz/DIinAGP

cs.SE↗

arXiv2025

FasterPy: An LLM-based Code Execution Efficiency Optimization Framework

Code often suffers from performance bugs. These bugs necessitate the research and practice of code optimization. Traditional rule-based methods rely on manually designing and maintaining rules for specific performance bugs (e.g., redundant loops, repeated computations), making them labor-intensive and limited in applicability. In recent years, machine learning and deep learning-based methods have emerged as promising alternatives by learning optimization heuristics from annotated code corpora and performance measurements. However, these approaches usually depend on specific program representations and meticulously crafted training datasets, making them costly to develop and difficult to scale. With the booming of Large Language Models (LLMs), their remarkable capabilities in code generation have opened new avenues for automated code optimization. In this work, we proposed FasterPy, a low-cost and efficient framework that adapts LLMs to optimize the execution efficiency of Python code. FasterPy combines Retrieval-Augmented Generation (RAG), supported by a knowledge base constructed from existing performance-improving code pairs and corresponding performance measurements, with Low-Rank Adaptation (LoRA) to enhance code optimization performance. Our experimental results on the Performance Improving Code Edits (PIE) benchmark demonstrate that our method outperforms existing models on multiple metrics. The FasterPy tool and the experimental results are available at https://github.com/WuYue22/fasterpy.

cs.SE↗

arXiv2025

Finding Compiler Bugs through Cross-Language Code Generator and Differential Testing

Compilers play a central role in translating high-level code into executable programs, making their correctness essential for ensuring code safety and reliability. While extensive research has focused on verifying the correctness of compilers for single-language compilation, the correctness of cross-language compilation - which involves the interaction between two languages and their respective compilers - remains largely unexplored. To fill this research gap, we propose CrossLangFuzzer, a novel framework that introduces a universal intermediate representation (IR) for JVM-based languages and automatically generates cross-language test programs with diverse type parameters and complex inheritance structures. After generating the initial IR, CrossLangFuzzer applies three mutation techniques - LangShuffler, FunctionRemoval, and TypeChanger - to enhance program diversity. By evaluating both the original and mutated programs across multiple compiler versions, CrossLangFuzzer successfully uncovered 10 confirmed bugs in the Kotlin compiler, 4 confirmed bugs in the Groovy compiler, 7 confirmed bugs in the Scala 3 compiler, 2 confirmed bugs in the Scala 2 compiler, and 1 confirmed bug in the Java compiler. Among all mutators, TypeChanger is the most effective, detecting 11 of the 24 compiler bugs. Furthermore, we analyze the symptoms and root causes of cross-compilation bugs, examining the respective responsibilities of language compilers when incorrect behavior occurs during cross-language compilation. To the best of our knowledge, this is the firstwork specifically focused on identifying and diagnosing compiler bugs in cross-language compilation scenarios. Our research helps to understand these challenges and contributes to improving compiler correctness in multi-language environments.

cs.PL↗

arXiv2024

A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Code Smell Detection

Automated code smell detection faces persistent challenges due to the subjectivity of heuristic rules and the limited performance of traditional ML/DL models. While Large Language Models (LLMs) offer a promising alternative, their adoption is impeded by high fine-tuning costs and a lack of "LM-ready" benchmarks. To bridge these gaps, we present a study with two synergistic contributions. First, we constructed a high-quality benchmark for Complex Conditional, Complex Method, Feature Envy, and Data Class, validated through a rigorous two-stage manual review. Second, leveraging this benchmark, we systematically evaluated four Parameter-Efficient Fine-Tuning (PEFT) methods across nine LMs of varying parameter sizes. Their performance is compared against a comprehensive suite of baselines, including heuristics-based detectors, Deep Learning (DL)-based approaches, and state-of-the-art general-purpose LLMs under multiple In-Context Learning (ICL) settings. Our results demonstrate that PEFT methods achieve effectiveness comparable to or surpassing full fine-tuning while substantially reducing peak GPU memory usage for code smell detection. Furthermore, PEFT-tuned LMs consistently outperform all baselines, yielding MCC improvements ranging from 0.33% to 13.69%, with particularly notable gains for specific smell categories. These findings highlight PEFT techniques as effective and scalable solutions for advancing code smell detection.

cs.SE↗

arXiv2024

Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair

LLMs have garnered considerable attention for their potential to streamline Automated Program Repair (APR). LLM-based approaches can either insert the correct code or directly generate patches when provided with buggy methods. However, most of LLM-based APR methods rely on a single type of software information, without fully leveraging different software artifacts. Despite this, many LLM-based approaches do not explore which specific types of information best assist in APR. Addressing this gap is crucial for advancing LLM-based APR techniques. We propose DEVLoRe to use issue content (description and message) and stack error traces to localize buggy methods, then rely on debug information in buggy methods and issue content and stack error to localize buggy lines and generate plausible patches which can pass all unit tests. The results show that while issue content is particularly effective in assisting LLMs with fault localization and program repair, different types of software artifacts complement each other. By incorporating different artifacts, DEVLoRe successfully locates 49.3% and 47.6% of single and non-single buggy methods and generates 56.0% and 14.5% plausible patches for the Defects4J v2.0 dataset, respectively. This outperforms current state-of-the-art APR methods. Furthermore, we re-implemented and evaluated our framework, demonstrating its effectiveness in its effectiveness in resolving 9 unique issues compared to other state-of-the-art frameworks using the same or more advanced models on SWE-bench Lite.We also discussed whether a leading framework for Python code can be directly applied to Java code, or vice versa. The source code and experimental results of this work for replication are available at https://github.com/XYZboom/DEVLoRe.

cs.SE↗

arXiv2024

Copilot-in-the-Loop: Fixing Code Smells in Copilot-Generated Python Code using Copilot

As one of the most popular dynamic languages, Python experiences a decrease in readability and maintainability when code smells are present. Recent advancements in Large Language Models have sparked growing interest in AI-enabled tools for both code generation and refactoring. GitHub Copilot is one such tool that has gained widespread usage. Copilot Chat, released in September 2023, functions as an interactive tool aimed at facilitating natural language-powered coding. However, limited attention has been given to understanding code smells in Copilot-generated Python code and Copilot Chat's ability to fix the code smells. To this end, we built a dataset comprising 102 code smells in Copilot-generated Python code. Our aim is to first explore the occurrence of code smells in Copilot-generated Python code and then evaluate the effectiveness of Copilot Chat in fixing these code smells employing different prompts. The results show that 8 out of 10 types of code smells can be detected in Copilot-generated Python code, among which Multiply-Nested Container is the most common one. For these code smells, Copilot Chat achieves a highest fixing rate of 87.1%, showing promise in fixing Python code smells generated by Copilot itself. In addition, the effectiveness of Copilot Chat in fixing these smells can be improved by providing more detailed prompts.

cs.SE↗

arXiv2024

Depends-Kotlin: A Cross-Language Kotlin Dependency Extractor

Since Google introduced Kotlin as an official programming language for developing Android apps in 2017, Kotlin has gained widespread adoption in Android development. However, compared to Java, there is limited support for Kotlin code dependency analysis, which is the foundation to software analysis. To bridge this gap, we develop Depends-Kotlin to extract entities and their dependencies in Kotlin source code. Not only does Depends-Kotlin support extracting entities' dependencies in Kotlin code, but it can also extract dependency relations between Kotlin and Java. Using three open-source Kotlin-Java mixing projects as our subjects, Depends-Kotlin demonstrates high accuracy and performance in resolving Kotlin-Kotlin and Kotlin-Java dependencies relations. The source code of Depends-Kotlin and the dataset used have been made available at https: //github.com/XYZboom/depends-kotlin. We also provide a screen-cast presenting Depends-Kotlin at https://youtu.be/ZPq8SRhgXzM.

cs.SE↗

arXiv2024

An Empirical Study of Kotlin-Java Cross-Dependency Issues and Their Detection

Since Google introduced Kotlin as an official programming language for developing Android apps in 2017, Kotlin has gained widespread adoption in Android development. The interoperability of Java and Kotlin's design nature allows them to coexist and interact with each other smoothly within a project. However, there is limited research on how Java and Kotlin interact with each other in real-world projects and what challenges are faced during these interactions. The answers to these questions are key to understanding these kinds of cross-language software systems. In this paper, we implemented a tool; named DependExtractor, which can extract 11 types and 9 types of Kotlin-Java and Java-Kotlin dependencies, and conducted an empirical study of 40 Kotlin-Java real-world projects with 27,427 Java and 36,141 Kotlin source files. Our findings revealed that Java and Kotlin frequently interact with each other in these cross-language projects, with Access and Call dependency types being the most dominant. Compared to files interacting with other files in the same language, Java/Kotlin source files, which participate in the cross-language interactions, experience more commits and exhibit a higher defect rate. Additionally, among all Kotlin-Java problematic interactions, we identified ten common issues, along with their fixing strategies. Furthermore, we implemented a tool called InteropScan to proactively detect these issues from Java and Kotlin source code. The findings of this study can help developers understand and address the challenges in Kotlin-Java projects.

cs.SE↗

arXiv2023

An Empirical Study of Untangling Patterns of Two-Class Dependency Cycles

Dependency cycles pose a significant challenge to software quality and maintainability. However, there is limited understanding of how practitioners resolve dependency cycles in real-world scenarios. This paper presents an empirical study investigating the recurring patterns employed by software developers to resolve dependency cycles between two classes in practice. We analyzed the data from 38 open-source projects across different domains and manually inspected hundreds of cycle untangling cases. Our findings reveal that developers tend to employ five recurring patterns to address dependency cycles. The chosen patterns are not only determined by dependency relations between cyclic classes, but also highly related to their design context, i.e., how cyclic classes depend on or are depended by their neighbor classes. Through this empirical study, we also discovered three common counterintuitive solutions developers usually adopted during cycles' handling. These recurring patterns and common counterintuitive solutions observed in dependency cycles' practice can serve as a taxonomy to improve developers' awareness and also be used as learning materials for students in software engineering and inexperienced developers. Our results also suggest that, in addition to considering the internal structure of dependency cycles, automatic tools need to consider the design context of cycles to provide better support for refactoring dependency cycles.

cs.SE↗

arXiv2023

Graph-based Village Level Poverty Identification

Poverty status identification is the first obstacle to eradicating poverty. Village-level poverty identification is very challenging due to the arduous field investigation and insufficient information. The development of the Web infrastructure and its modeling tools provides fresh approaches to identifying poor villages. Upon those techniques, we build a village graph for village poverty status identification. By modeling the village connections as a graph through the geographic distance, we show the correlation between village poverty status and its graph topological position and identify two key factors (Centrality, Homophily Decaying effect) for identifying villages. We further propose the first graph-based method to identify poor villages. It includes a global Centrality2Vec module to embed village centrality into the dense vector and a local graph distance convolution module that captures the decaying effect. In this paper, we make the first attempt to interpret and identify village-level poverty from a graph perspective.

cs.CY↗

arXiv2018

A Longitudinal Study of Identifying and Paying Down Architectural Debt

Architectural debt is a form of technical debt that derives from the gap between the architectural design of the system as it "should be" compared to "as it is". We measured architecture debt in two ways: 1) in terms of system-wide coupling measures, and 2) in terms of the number and severity of architectural flaws. In recent work it was shown that the amount of architectural debt has a huge impact on software maintainability and evolution. Consequently, detecting and reducing the debt is expected to make software more amenable to change. This paper reports on a longitudinal study of a healthcare communications product created by Brightsquid Secure Communications Corp. This start-up company is facing the typical trade-off problem of desiring responsiveness to change requests, but wanting to avoid the ever-increasing effort that the accumulation of quick-and-dirty changes eventually incurs. In the first stage of the study, we analyzed the status of the "before" system, which indicated the impacts of change requests. This initial study motivated a more in-depth analysis of architectural debt. The results of this analysis were used to motivate a comprehensive refactoring of the software system. The third phase of the study was a follow-on architectural debt analysis which quantified the improvements made. Using this quantitative evidence, augmented by qualitative evidence gathered from in-depth interviews with Brightsquid's architects, we present lessons learned about the costs and benefits of paying down architecture debt in practice.

cs.SE↗

arXiv2016

Dislocation Activities at the Martensite Phase Transformation Interface in Metastable Austenitic Stainless Steel: An In-situ TEM Study

Understanding the mechanism of martensitic transformation is of great importance in developing advanced high strength steels, especially TRansformation-Induced Plasticity (TRIP) steels. The TRIP effect leads to enhanced work-hardening rate, postponed onset of necking and excellent formability. In-situ transmission electron microscopy has been performed to systematically investigate the dynamic interactions between dislocations and alpha martensite at microscale. Local stress concentrations, e.g. from notches or dislocation pile-ups, render free edges and grain boundaries favorable nucleation sites for alpha martensite. Its growth leads to partial dislocation emission on two independent slip planes from the hetero-interface when the austenite matrix is initially free of dislocations. The kinematic analysis reveals that activating slip systems on two independent {111} planes of austenite are necessary in accommodating the interfacial mismatch strain. Full dislocation emission is generally observed inside of austenite regions that contain high density of dislocations. In both situations, phase boundary propagation generates large amounts of dislocations entering into the matrix, which renders the total deformation compatible and provide substantial strain hardening of the host phase. These moving dislocation sources enable plastic relaxation and prevent local damage accumulation by intense slipping on the softer side of the interfacial region. Thus, finely dispersed martensite distribution renders plastic deformation more uniform throughout the austenitic matrix, which explains the exceptional combination of strength and ductility of TRIP steels.

cond-mat.mtrl-sci↗