软件工程

Automated Program Repair (APR) aims to automatically generate correct patches for buggy programs. Recent approaches leveraging large language models (LLMs) have shown promise but face limitations. Most rely solely on static analysis,…

Code smell is a great challenge in software refactoring, which indicates latent design or implementation flaws that may degrade the software maintainability and evolution. Over the past decades, a variety of refactoring approaches have been…

We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse…

Large Language Models (LLMs) have become central to automated code generation, yet existing approaches operate within a single-LLM paradigm: one model is selected and applied throughout the entire generation process. We observe that…

Efficient, interpretable optimization is a critical but underexplored challenge in software engineering, where practitioners routinely face vast configuration spaces and costly, error-prone labeling processes. This paper introduces EZR, a…

Code Language Models (CodeLLMs) traditionally learn attention based solely on statistical input-output token correlations ("machine attention"). In contrast, human developers rely on intuition, selectively fixating on semantically salient…

Large language models excel at code generation but struggle with code linting, particularly in generalizing to unseen or evolving best practices beyond those observed during training. We introduce MetaLint, a meta-learning framework that…

Pre-trained models (PTMs) have gained widespread popularity and achieved remarkable success across various fields, driven by their groundbreaking performance and easy accessibility through hosting providers. However, the challenges faced by…

Current research on large language models (LLMs) with retrieval-augmented code generation (RACG) has largely focused on single-language settings, leaving their cross-lingual effectiveness underexplored. Multilingual RACG systems are…

There has been a growing interest in translating C code to Rust due to Rust's robust memory and thread safety guarantees. Tools such as C2RUST enable syntax-guided transpilation from C to semantically equivalent Rust code. However, the…

To ensure the quality of software systems, software engineers can make use of a variety of quality assurance approaches, such as software testing, modern code review, automated static analysis, and build automation. Each of these quality…

The JavaScript language did not specify, until ECMAScript 6 (ES6), native features for streamlining encapsulation and modularity. Developer community filled the gap with a proliferation of design patterns and module formats, with impact on…

Software engineering research has experienced rapid growth in both output and participation over the past decades. Yet concerns persist about the field's ability to accumulate, integrate, and reuse knowledge in ways that support long-term…

Code generation refers to automatically producing executable programs from user requirements. Recently, researchers have explored approaches to enhance the correctness of generated code with advanced large language models. Although…

The rapid proliferation of Large Language Models (LLMs) in software development has made distinguishing AI-generated code from human-written code a critical challenge with implications for academic integrity, code quality assurance, and…

A lot of research relies on data analysis scripts to process, clean, and visualize data. However, recent studies show that these scripts are often hard to comprehend and maintain, hindering reproducibility and reuse, accompanied by a lack…

Many small-scale software systems, that is, with limited codebase or binary size, are widely used in everyday tasks, yet their configurability remains largely unexplored. At the same time, studies on modern software systems show a trend…

Feature toggles enable gradual rollouts and experimentation in software systems, yet often persist beyond their intended lifecycle, accumulating as technical debt. Prior research has examined feature toggle interactions and complexity, but…

Quantum software testing has attracted interest in recent years, prompting the development of various techniques to automate the testing of quantum software. These techniques generate test cases that must be assessed for their effectiveness…

Code search, framed as information retrieval (IR), underpins modern software engineering and increasingly powers retrieval-augmented generation (RAG), improving code discovery, reuse, and the reliability of LLM-based coding. Yet existing…