软件工程
Large language models (LLMs) have become essential tools in software development, widely used for requirements engineering, code generation and review tasks. Software engineers often rely on LLMs to verify if code implementation satisfy…
The SWE-Bench Verified leaderboard is approaching saturation, with the top system achieving 78.80%. However, we show that this performance is inflated. Our re-evaluation reveals that one in five "solved" patches from the top-30 agents are…
The README file serves as a critical source of information for gaining an overview and helping developers onboard to an Open Source Software (OSS) project. Yet, documentation issues persist; in particular, ``outdated'' documentation is…
The transition to agentic Root Cause Analysis (RCA) necessitates benchmarks that evaluate active reasoning rather than passive classification. However, current frameworks fail to reconcile ecological validity with reproducibility. We…
Software engineers use regular expressions (regexes) across a wide range of domains and tasks. To support regexes, software projects must integrate a regex engine, whether provided natively by the language runtime (e.g., Python's re) or…
LLM agents are increasingly used for code generation, but physics-based simulation poses a deeper challenge: natural-language descriptions of simulation models are inherently underspecified, and different admissible resolutions of implicit…
To integrate seamlessly into real-world software engineering, Code Agents must evolve from passive instruction followers into proactive collaborative partners. However, current evaluation paradigms predominantly reward "guessing" user…
Bug severity prediction is important in software maintenance, because it helps the development teams to prioritize bugs that have a significant impact on the operation, stability and security of the system. In large software projects bug…
CI/CD practices play a significant role during collaborative software development by automating time-consuming and repetitive tasks such as testing, building, quality checking, dependency and security management. GitHub Actions, the CI/CD…
We present GraphCue, a topology-grounded retrieval and agent-in-the-loop framework for automated SDN configuration. Each case is abstracted into a JSON graph and embedded using a lightweight three-layer GCN trained with contrastive…
Data science initiatives frequently exhibit high failure rates, driven by technical constraints, organizational limitations and insufficient risk management practices. Challenges such as low data maturity, lack of governance, misalignment…
The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outputs that can be dangerous. This paper introduces the Formal…
Automated unit test generation is essential for robust software development, yet existing approaches struggle to generalize across multiple programming languages and operate within real-time development. While Large Language Models (LLMs)…
JavaScript obfuscators are widely deployed to protect intellectual property and resist reverse engineering, yet their correctness has been largely overlooked compared to performance and resilience. Existing evaluations typically measure…
Large language model (LLM) agents have demonstrated strong capabilities in long-horizon tasks by interleaving reasoning with tool use. However, as these agents scale to complex workflows such as software engineering and open-ended research,…
Software obfuscation, particularly prevalent in JavaScript, hinders code comprehension and analysis, posing significant challenges to software testing, static analysis, and malware detection. This paper introduces CASCADE, a novel hybrid…
Large Language Models (LLMs) are widely used for automated code generation. Their reliance on infrequently updated pretraining data leaves them unaware of newly discovered vulnerabilities and evolving security standards, making them prone…
Alloy is a well-known, formal, declarative language for modelling systems early in the software development process. Currently, it uses the Kodkod library as a back-end for finite model finding. Kodkod translates the model to a SAT problem;…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance on the design-to-code task, i.e., generating UI code from UI mock-ups. However, existing benchmarks only contain static web pages for evaluation and ignore…
Over the past decade, modern code review (MCR) has been established as a cornerstone of software quality assurance and a vital channel for knowledge transfer within development teams. However, the manual inspection of increasingly complex…