软件工程
Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-level software engineering (SWE), which demands (1) deep codebase navigation with effective context…
Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically treat this as a repository-level retrieval task and rely on…
We present BIOMERO 2.0, a major evolution of the BIOMERO framework that transforms OMERO into a FAIR-compliant (findable, accessible, interoperable, and reusable), provenance-aware bioimaging platform. BIOMERO 2.0 integrates data import,…
To ensure their safe use, autonomous vehicles (AVs) must meet rigorous certification criteria that involve executing maneuvers safely within (arbitrary) scenarios where other actors perform their intended maneuvers. For that purpose,…
Code review is a critical practice in software engineering, yet the growing scale and frequency of code patches in modern projects, together with the widespread adoption of AI code assistants, make manual review increasingly challenging.…
Generating code from natural-language requirements has become a primary route for LLM-assisted software development. Although LLMs can successfully complete small programming tasks, generating an entire complex project remains unreliable…
Log parsing is a fundamental step for automated log analysis, which transforms raw log messages into structured formats. Existing syntax-based parsers struggle with complex logs because they lack semantic reasoning ability. Emerging…
Generative AI tools are rapidly transforming software development practice, prompting unprecedented research interest. However, existing studies have predominantly examined initial adoption rather than sustained use. Understanding what…
Agentic AI coding assistants can edit files, run commands, and access the internet on behalf of developers. However, their reliance on unvetted external artifacts introduces a new attack vector. Hidden instructions in external artifacts can…
AI-native software development is often evaluated at the level of individual models, prompts, or generated artifacts. This framing is insufficient for production environments where software must be continuously produced, verified, deployed,…
Context. Large language models (LLMs) are increasingly applied to code-generating tasks (CGTs) in software engineering. While reported results are promising, the broader effects of such application and their integration into real-world…
Responsive Layout Failures (RLFs) typically arise from CSS properties that hinder proper layout behavior in different screen sizes. To find an accurate and effective solution for repairing RLFs, localization of those problematic properties…
Log statements capture critical information for software maintenance activities such as testing, debugging, and failure analysis. Because of this importance, developers must carefully design log statements, which requires significant…
Regression test selection reduces the cost of regression testing by executing only those tests affected by a code change. Despite extensive study of RTS in statically typed languages, achieving effective and safe RTS in Python is…
Automated test generation has a substantial body of work, yet most studies focus on generating tests for complete software units, such as classes, and rely on metrics such as code coverage for assessment. In contrast, modern software…
Direct Code2Code transformation remains challenging to control because it can preserve surface-level syntax while introducing semantic drift, hidden behavioral changes, loss of traceability, non-idiomatic target implementations, or…
In many industrial domains, the Functional Mock-up Interface (FMI) is used to exchange simulation models as Functional Mock-up Units (FMUs) across different partners using various modelling tools. This opens up the possibilities for…
Distributed protocols are notoriously difficult to verify correctly. Proving safety typically requires inductive invariants that both imply the desired property and are preserved by every protocol transition; yet inferring such invariants…
AI code generation tools have expanded software creation beyond professional developers, giving rise to vibe coding, a practice in which users generate software via natural-language prompts, evaluate outputs primarily by execution. Prior…
Microservices have become a mainstream architectural paradigm, yet microservice bad smells can significantly harm maintainability and performance. Existing detection tools often produce obscure outputs and lack effective integration with…