软件工程
The lack of transparency about code datasets used to train large language models (LLMs) makes it difficult to detect, evaluate, and mitigate data leakage. We present a perturbation-based method to quantify memorization advantage in code…
Software engineering research has focused on automating maintenance and evolution processes to reduce costs and improve reliability. The emergence of foundation models (FMs) with strong code understanding and reasoning abilities offers new…
Sentiment analysis in software engineering focuses on understanding emotions expressed in software artifacts. Previous research highlighted the limitations of applying general off-the-shelf sentiment analysis tools within the software…
Merging is a core operation in version control systems such as Git, but traditional line-based algorithms often yield spurious conflicts, particularly in the presence of refactorings or parallel edits. While syntax- and semantics-aware…
Deep Learning (DL) is becoming more and more widespread in clone detection, motivated by achieving near-perfect performance for this task. In particular in case of semantic code clones, which share only limited syntax but implement the same…
Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…
Performance debugging in WebAssembly (Wasm) runtimes is essential for ensuring the robustness of Wasm, especially since performance issues have frequently occurred in Wasm runtimes, which can significantly degrade the capabilities of hosted…
Front-end development constitutes a substantial portion of software engineering, yet converting design mockups into production-ready User Interface (UI) code remains tedious and costly. While recent work has explored automating this process…
Scenario testing is an important technique for detecting errors in web systems. Testers draft test scenarios and convert them into test scripts for execution. Early methods relied on testers to convert test scenarios into test scripts.…
Mobile apps often suffer from functional bugs that do not cause crashes but instead manifest as incorrect behaviors under specific user interactions. Such bugs are difficult to detect automatically because they often lack explicit test…
Effective IT change management is important for businesses that depend on software and services, particularly in highly regulated sectors such as finance, where operational reliability, auditability, and explainability are essential. A…
As Large Language Models (LLMs) are increasingly deployed in mission-critical software systems, detecting hallucinations and ``faked truthfulness'' has become a paramount engineering challenge. Current reliability architectures rely heavily…
Generative Artificial Intelligence (GenAI) tools (e.g., ChatGPT, Calude) have rapidly become integral to software development. These tools are especially attractive to students, as they can reduce cognitive load. However, their adoption…
Continuous Integration/Continuous Delivery (CI/CD) caching is widely used to reduce repeated computation and improve CI/CD efficiency, yet maintaining effective caching requires ongoing maintenance effort. In this paper, we present the…
Large language models generate plausible code but cannot verify correctness. Existing multi-agent systems simulate execution or leave verification optional. We introduce execution-grounded verification as a first-class principle: every code…
Cyber-Physical Systems (CPS) produce behavior through execution on substrates coupling computation with physical processes. However, usual engineering approaches do not treat execution semantics as first-class engineering entities. Formal…
Code smells and software vulnerabilities both increase maintenance cost, yet they are often handled by separate tools that miss structural context and produce noisy warnings. This paper presents The Code Whisperer, a hybrid framework that…
We present a two-stage pipeline for AI-assisted improvement of published algorithm implementations. In the first stage, a large language model with research capabilities identifies recently published algorithms satisfying explicit…
AI coding agents spend a substantial fraction of their tool calls on undirected codebase exploration. We investigate whether providing agents with formal architecture descriptors can reduce this navigational overhead. We present three…
As coding agents have seen rapid capability and adoption gains, users are applying them to general tasks beyond software engineering. In this post, we investigate whether coding agents can successfully generalize to end-to-end business…