Exploring the Potential of Large Language Models in Fine-Grained Review Comment Classification. arxiv.org/abs/2508.09832

An Empirical Study of CGO Usage in Go Projects -- Distribution, Purposes, Patterns and Critical Issues. arxiv.org/abs/2508.09875

ARI3D: A Software for Interactive Quantification of Regions in X-Ray CT 3D Images. arxiv.org/abs/2508.09849

VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs. arxiv.org/abs/2408.04125

Leveraging Reviewer Experience in Code Review Comment Generation. arxiv.org/abs/2409.10959

AUCAD: Automated Construction of Alignment Dataset from Log-Related Issues for Enhancing LLM-based Log Generation. arxiv.org/abs/2412.18835

Can Automated Feedback Turn Students into Happy Prologians?. arxiv.org/abs/2504.16742

FormalGrad: Integrating Formal Methods with Gradient-Based LLM Refinement. arxiv.org/abs/2508.10059

Next Edit Prediction: Learning to Predict Code Edits from Context and Interaction History. arxiv.org/abs/2508.10074

On the synchronization between Hugging Face pre-trained language models and their upstream GitHub repository. arxiv.org/abs/2508.10157

Bridging Solidity Evolution Gaps: An LLM-Enhanced Approach for Smart Contract Compilation Error Resolution. arxiv.org/abs/2508.10517

EVOSCAT: Exploring Software Change Dynamics in Large-Scale Historical Datasets. arxiv.org/abs/2508.10852

Enabling Generic Robot Skill Implementation Using Object Oriented Programming. arxiv.org/abs/2508.10497

A Reference Architecture for Governance of Cloud Native Applications. arxiv.org/abs/2302.11617

A MAPE-K-Based Method for Architectural Conformance Checking in Self-Adaptive Systems. arxiv.org/abs/2401.16382

VERCATION: Precise Vulnerable Open-source Software Version Identification based on Static Analysis and LLM. arxiv.org/abs/2408.07321

Robustness tests for biomedical foundation models should tailor to specifications. arxiv.org/abs/2502.10374

Detec\c{c}\~ao de Conflitos Sem\^anticos com Testes Gerados por LLM. arxiv.org/abs/2507.06762

CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks. arxiv.org/abs/2507.10535

Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?. arxiv.org/abs/2507.21817