arXiv subjects

Yanjie Jiang

Publications and source records attributed to Yanjie Jiang.

14 recordsLinked to original sources

arXiv2026

From Custom Logic to APIs: Understanding and Recommending API Replacement Refactorings

Software refactoring is essential for maintaining code quality. However, API replacement refactoring, which replaces custom logic with API calls, remains underexplored. Existing refactoring tools provide limited support for detecting such opportunities because they rely on predefined templates and have difficulty capturing complex, multi-statement semantic equivalents. To address this limitation, we conduct the first empirical study of API replacement refactorings by mining 166,299 commits across six open-source Java projects and manually analyzing a curated subset of 1,800 commits, from which we identify 366 validated instances to characterize their scope, categories, and recurring patterns. Based on these insights, we propose AKIRA (Adaptive Knowledge Discovery and Retrieval), a hybrid framework that integrates pattern-deterministic heuristics with a refactoring-aware knowledge base to assess the practical feasibility of recommending API replacement refactorings. Our evaluation shows that AKIRA achieves 90% recall and 88% precision on a manually curated dataset. Furthermore, on the external RETIWA dataset, AKIRA significantly improves the state of the art by increasing recall from 21% to 81% and precision from 40% to 78%. These results demonstrate the effectiveness of combining static pattern matching with semantic reasoning to support the automation of recommending complex API replacement refactorings.

cs.SE↗

arXiv2026

Characterizing the Failure Modes of LLMs in Resolving Real-World GitHub Issues

Large Language Models (LLMs) are increasingly deployed to resolve real-world GitHub issues. However, despite their potential, the specific failure modes of these models in complex repair tasks remain poorly understood. To characterize how LLM behavior diverges from human developer practices, this paper evaluates three state-of-the-art models, i.e., Claude 4.5 Sonnet, Gemini 3 Pro, and GPT-5, on the SWE-bench Verified dataset. We conduct a rigorous manual analysis of the symptoms and root causes underlying 243 failed attempts across 900 total trials. Our investigation first yields a unified failure taxonomy encompassing five distinct stages of the repair pipeline, within which we categorize typical failure symptoms and their prevalence. Secondly, our findings reveal that for all evaluated LLMs, strategy formulation and logic synthesis constitutes the most error-prone stage, followed by problem understanding, whereas localization exhibits the lowest failure rate. This suggests that LLMs may excel at fault localization, a task traditionally regarded as one of the most formidable challenges in automated program repair. Furthermore, we observe that robustness and operational costs (particularly in failure scenarios) vary significantly across different models. Finally, we uncover the root causes of these failures and propose actionable strategies to mitigate them. A particularly notable finding is that existing evaluation harnesses occasionally misjudge correct patches due to superficial discrepancies or hidden constraints. Collectively, our insights may provide promising directions for enhancing the effectiveness and reliability of LLM-based issue resolution.

cs.SE↗

arXiv2026

LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLM

Code review is critical for ensuring software quality and maintainability. With the rapid growth in software scale and complexity, code review has become a bottleneck in the development process because of its time-consuming and knowledge-intensive nature and the shortage of experienced developers willing to review code. Several approaches have been proposed for automatically generating code reviews based on retrieval, neural machine translation, pre-trained models, or large language models (LLMs). These approaches mainly leverage historical code changes and review comments. However, a large amount of crucial information for code review, such as the context of code changes and prior review knowledge, has been overlooked. This paper proposes an LLM-based review knowledge-augmented, context-aware framework for code review generation, named LAURA. The framework integrates review exemplar retrieval, context augmentation, and systematic guidance to enhance the performance of ChatGPT-4o and DeepSeek v3 in generating code review comments. Besides, given the extensive low-quality reviews in existing datasets, we also constructed a high-quality dataset. Experimental results show that for both models, LAURA generates review comments that are either completely correct or at least helpful to developers in 42.2% and 40.4% of cases, respectively, significantly outperforming SOTA baselines. Furthermore, our ablation studies demonstrate that all components of LAURA contribute positively to improving comment quality.

cs.SE↗

arXiv2026

SeRe: A Security-Related Code Review Dataset Aligned with Real-World Review Activities

Software security vulnerabilities can lead to severe consequences, making early detection essential. Although code review serves as a critical defense mechanism against security flaws, relevant feedback remains scarce due to limited attention to security issues or a lack of expertise among reviewers. Existing datasets and studies primarily focus on general-purpose code review comments, either lacking security-specific annotations or being too limited in scale to support large-scale research. To bridge this gap, we introduce \textbf{SeRe}, a \textbf{security-related code review dataset}, constructed using an active learning-based ensemble classification approach. The proposed approach iteratively refines model predictions through human annotations, achieving high precision while maintaining reasonable recall. Using the fine-tuned ensemble classifier, we extracted 6,732 security-related reviews from 373,824 raw review instances, ensuring representativeness across multiple programming languages. Statistical analysis indicates that SeRe generally \textbf{aligns with real-world security-related review distribution}. To assess both the utility of SeRe and the effectiveness of existing code review comment generation approaches, we benchmark state-of-the-art approaches on security-related feedback generation. By releasing SeRe along with our benchmark results, we aim to advance research in automated security-focused code review and contribute to the development of more effective secure software engineering practices.

cs.SE↗

arXiv2025

Condor: A Code Discriminator Integrating General Semantics with Code Details

LLMs demonstrate significant potential across various software engineering tasks. However, they still face challenges in generating correct code on the first attempt when addressing complex requirements. Introducing a discriminator to select reliable outputs from multiple generated results is an effective way to enhance their reliability and stability. Currently, these discriminators fall into two categories: execution-based discriminators and non-execution-based discriminators. Execution-based discriminators face flexibility challenges due to difficulties in obtaining test cases and security concerns, while non-execution-based discriminators, although more flexible, struggle to capture subtle differences in code details. To maintain flexibility while improving the model's ability to capture fine-grained code details, this paper proposes Condor. We first design contrastive learning to optimize the code representations of the base model, enabling it to reflect differences in code details. Then, we leverage intermediate data from the code modification process to further enrich the discriminator's training data, enhancing its ability to discern code details. Experimental results indicate that on the subtle code difference dataset (i.e., CodeNanoFix), Condor significantly outperforms other discriminators in discriminative performance: Condor (1.3B) improves the discriminative F1 score of DeepSeek-Coder (1.3B) from 67% to 73%. In discriminating LLM-generated outputs, Condor (1.3B) and Condor (110M) raise the Pass@1 score of Meta-Llama-3.1-Instruct (70B) on the CodeNanoFix dataset from 52.64% to 62.63% and 59.64%, respectively. Moreover, Condor demonstrates strong generalization capabilities on the APPS, MBPP, and LiveCodeBench datasets. For example, Condor (1.3B) improves the Pass@1 of Meta-Llama-3.1-Instruct (70B) on the APPS dataset by 147.05%.

cs.SE↗

arXiv2025

Wired for Reuse: Automating Context-Aware Code Adaptation in IDEs via LLM-Based Agent

Copy-paste-modify is a widespread and pragmatic practice in software development, where developers adapt reused code snippets, sourced from platforms such as Stack Overflow, GitHub, or LLM outputs, into their local codebase. A critical yet underexplored aspect of this adaptation is code wiring: the context-aware process of substituting unresolved variables in pasted code with suitable variables or expressions from the surrounding context. Existing solutions either rely on heuristic rules or historical templates, often failing to effectively utilize contextual information, despite studies showing that over half of adaptation cases are context-dependent. In this paper, we introduce WIRL, an LLM-based agent for code wiring framed as a Retrieval-Augmented Generation (RAG) infilling task. WIRL combines an LLM, a customized toolkit, and an orchestration module to identify unresolved variables, retrieve context, and perform context-aware substitutions. To balance efficiency and autonomy, the agent adopts a mixed strategy: deterministic rule-based steps for common patterns, and a state-machine-guided decision process for intelligent exploration. We evaluate WIRL on a carefully curated, high-quality dataset consisting of real-world code adaptation scenarios. Our approach achieves an exact match precision of 91.7% and a recall of 90.0%, outperforming advanced LLMs by 22.6 and 13.7 percentage points in precision and recall, respectively, and surpassing IntelliJ IDEA by 54.3 and 49.9 percentage points. These results underscore its practical utility, particularly in contexts with complex variable dependencies or multiple unresolved variables. We believe WIRL paves the way for more intelligent and context-aware developer assistance in modern IDEs.

cs.SE↗

arXiv2025

Reflective Unit Test Generation for Precise Type Error Detection with Large Language Models

Type errors in Python often lead to runtime failures, posing significant challenges to software reliability and developer productivity. Existing static analysis tools aim to detect such errors without execution but frequently suffer from high false positive rates. Recently, unit test generation techniques offer great promise in achieving high test coverage, but they often struggle to produce bug-revealing tests without tailored guidance. To address these limitations, we present RTED, a novel type-aware test generation technique for automatically detecting Python type errors. Specifically, RTED combines step-by-step type constraint analysis with reflective validation to guide the test generation process and effectively suppress false positives. We evaluated RTED on two widely-used benchmarks, BugsInPy and TypeBugs. Experimental results show that RTED can detect 22-29 more benchmarked type errors than four state-of-the-art techniques. RTED is also capable of producing fewer false positives, achieving an improvement of 173.9%-245.9% in precision. Furthermore, RTED successfully discovered 12 previously unknown type errors from six real-world open-source Python projects.

cs.SE↗

arXiv2025

Recommending Variable Names for Extract Local Variable Refactorings

Extract local variable is one of the most popular refactorings, and most IDEs and refactoring tools provide automated support for this refactoring. However, we find approximately 70% of the names recommended by these IDEs are different from what developers manually constructed, adding additional renaming burdens to developers and providing limited assistance. In this paper, we introduce VarNamer, an automated approach designed to recommend variable names for extract local variable refactorings. Through a large-scale empirical study, we identify key contexts that are useful for composing variable names. Leveraging these insights, we developed a set of heuristic rules through program static analysis techniques and employ data mining techniques to recommend variable names effectively. Notably, some of our heuristic rules have been successfully integrated into Eclipse, where they are now distributed with the latest releases of the IDE. Evaluation demonstrates its superiority over state-of-the-art IDEs. Specifically, VarNamer significantly increases the chance of exact match by 52.6% compared to Eclipse and 40.7% compared to IntelliJ IDEA. We also evaluated the proposed approach with real-world extract local variable refactorings conducted in C++ projects, and the results suggest that the approach can achieve comparable performance on programming languages besides Java. It may suggest the generalizability of VarNamer. Finally, we designed and conducted a user study and the results of the user study suggest that our approach can speed up the refactoring by 27.8% and reduce 49.3% edits on the recommended variable names.

cs.SE↗

arXiv2025

Deep Assessment of Code Review Generation Approaches: Beyond Lexical Similarity

Code review is a standard practice for ensuring the quality of software projects, and recent research has focused extensively on automated code review. While significant advancements have been made in generating code reviews, the automated assessment of these reviews remains less explored, with existing approaches and metrics often proving inaccurate. Current metrics, such as BLEU, primarily rely on lexical similarity between generated and reference reviews. However, such metrics tend to underestimate reviews that articulate the expected issues in ways different from the references. In this paper, we explore how semantic similarity between generated and reference reviews can enhance the automated assessment of code reviews. We first present a benchmark called \textit{GradedReviews}, which is constructed by collecting real-world code reviews from open-source projects, generating reviews using state-of-the-art approaches, and manually assessing their quality. We then evaluate existing metrics for code review assessment using this benchmark, revealing their limitations. To address these limitations, we propose two novel semantic-based approaches for assessing code reviews. The first approach involves converting both the generated review and its reference into digital vectors using a deep learning model and then measuring their semantic similarity through Cosine similarity. The second approach generates a prompt based on the generated review and its reference, submits this prompt to ChatGPT, and requests ChatGPT to rate the generated review according to explicitly defined criteria. Our evaluation on the \textit{GradedReviews} benchmark indicates that the proposed semantic-based approaches significantly outperform existing state-of-the-art metrics in assessing generated code review, improving the correlation coefficient between the resulting scores and human scores from 0.22 to 0.47.

cs.SE↗

arXiv2024

An Empirical Study on the Potential of LLMs in Automated Software Refactoring

Recent advances in large language models (LLMs), make it potentially feasible to automatically refactor source code with LLMs. However, it remains unclear how well LLMs perform compared to human experts in conducting refactorings automatically and accurately. To fill this gap, in this paper, we conduct an empirical study to investigate the potential of LLMs in automated software refactoring, focusing on the identification of refactoring opportunities and the recommendation of refactoring solutions. We first construct a high-quality refactoring dataset comprising 180 real-world refactorings from 20 projects, and conduct the empirical study on the dataset. With the to-be-refactored Java documents as input, ChatGPT and Gemini identified only 28 and 7 respectively out of the 180 refactoring opportunities. However, explaining the expected refactoring subcategories and narrowing the search space in the prompts substantially increased the success rate of ChatGPT from 15.6% to 86.7%. Concerning the recommendation of refactoring solutions, ChatGPT recommended 176 refactoring solutions for the 180 refactorings, and 63.6% of the recommended solutions were comparable to (even better than) those constructed by human experts. However, 13 out of the 176 solutions suggested by ChatGPT and 9 out of the 137 solutions suggested by Gemini were unsafe in that they either changed the functionality of the source code or introduced syntax errors, which indicate the risk of LLM-based refactoring. To this end, we propose a detect-and-reapply tactic, called RefactoringMirror, to avoid such unsafe refactorings. By reapplying the identified refactorings to the original code using thoroughly tested refactoring engines, we can effectively mitigate the risks associated with LLM-based automated refactoring while still leveraging LLM's intelligence to obtain valuable refactoring recommendations.

cs.SE↗

arXiv2024

Evaluating and Improving ChatGPT-Based Expansion of Abbreviations

Source code identifiers often contain abbreviations. Such abbreviations may reduce the readability of the source code, which in turn hinders the maintenance of the software applications. To this end, accurate and automated approaches to expanding abbreviations in source code are desirable and abbreviation expansion has been intensively investigated. However, to the best of our knowledge, most existing approaches are heuristics, and none of them has even employed deep learning techniques, let alone the most advanced large language models (LLMs). LLMs have demonstrated cutting-edge performance in various software engineering tasks, and thus it has the potential to expand abbreviation automatically. To this end, in this paper, we present the first empirical study on LLM-based abbreviation expansion. Our evaluation results on a public benchmark suggest that ChatGPT is substantially less accurate than the state-of-the-art approach, reducing precision and recall by 28.2\% and 27.8\%, respectively. We manually analyzed the failed cases, and discovered the root causes for the failures: 1) Lack of contexts and 2) Inability to recognize abbreviations. In response to the first cause, we investigated the effect of various contexts and found surrounding source code is the best selection. In response to the second cause, we designed an iterative approach that identifies and explicitly marks missed abbreviations in prompts. Finally, we proposed a post-condition checking to exclude incorrect expansions that violate commonsense. All such measures together make ChatGPT-based abbreviation expansion comparable to the state of the art while avoiding expensive source code parsing and deep analysis that are indispensable for state-of-the-art approaches.

cs.SE↗

arXiv2024

Deep Learning-based Software Engineering: Progress, Challenges, and Opportunities

Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software refactoring, and fault localization. Many papers have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various software engineering tasks. However, although several surveys have provided overall pictures of the application of deep learning techniques in software engineering, they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for software engineering tasks. We still lack surveys explaining the advances of subareas in software engineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this paper, we present the first task-oriented survey on deep learning-based software engineering. It covers twelve major software engineering subareas significantly impacted by deep learning techniques. Such subareas spread out the through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of software engineering, providing one survey covering as many subareas as possible in software engineering can help future research push forward the frontier of deep learning-based software engineering more systematically.

cs.SE↗

arXiv2024

A Survey of Deep Learning Based Software Refactoring

Refactoring is one of the most important activities in software engineering which is used to improve the quality of a software system. With the advancement of deep learning techniques, researchers are attempting to apply deep learning techniques to software refactoring. Consequently, dozens of deep learning-based refactoring approaches have been proposed. However, there is a lack of comprehensive reviews on such works as well as a taxonomy for deep learning-based refactoring. To this end, in this paper, we present a survey on deep learning-based software refactoring. We classify related works into five categories according to the major tasks they cover. Among these categories, we further present key aspects (i.e., code smell types, refactoring types, training strategies, and evaluation) to give insight into the details of the technologies that have supported refactoring through deep learning. The classification indicates that there is an imbalance in the adoption of deep learning techniques for the process of refactoring. Most of the deep learning techniques have been used for the detection of code smells and the recommendation of refactoring solutions as found in 56.25\% and 33.33\% of the literature respectively. In contrast, only 6.25\% and 4.17\% were towards the end-to-end code transformation as refactoring and the mining of refactorings, respectively. Notably, we found no literature representation for the quality assurance for refactoring. We also observe that most of the deep learning techniques have been used to support refactoring processes occurring at the method level whereas classes and variables attracted minimal attention. Finally, we discuss the challenges and limitations associated with the employment of deep learning-based refactorings and present some potential research opportunities for future work.

cs.SE↗

arXiv2021

Extracting Concise Bug-Fixing Patches from Human-Written Patches in Version Control Systems

High-quality and large-scale repositories of real bugs and their concise patches collected from real-world applications are critical for research in software engineering community. In such a repository, each real bug is explicitly associated with its fix. Therefore, on one side, the real bugs and their fixes} may inspire novel approaches for finding, locating, and repairing software bugs; on the other side, the real bugs and their fixes are indispensable for rigorous and meaningful evaluation of approaches for software testing, fault localization, and program repair. To this end, a number of such repositories, e.g., Defects4J, have been proposed. However, such repositories are rather small because their construction involves expensive human intervention. Although bug-fixing code commits as well as associated test cases could be retrieved from version control systems automatically, existing approaches could not yet automatically extract concise bug-fixing patches from bug-fixing commits because such commits often involve bug-irrelevant changes. In this paper, we propose an automatic approach, called BugBuilder, to extracting complete and concise bug-fixing patches from human-written patches in version control systems. It excludes refactorings by detecting refactorings involved in bug-fixing commits, and reapplying detected refactorings on the faulty version. It enumerates all subsets of the remaining part and validates them on test cases. If none of the subsets has the potential to be a complete bug-fixing patch, the remaining part as a whole is taken as a complete and concise bug-fixing patch. Evaluation results on 809 real bug-fixing commits in Defects4J suggest that BugBuilder successfully generated complete and concise bug-fixing patches for forty percent of the bug-fixing commits, and its precision (99%) was even higher than human experts.

cs.SE↗