arXiv subjects

Rian Melo

Publications and source records attributed to Rian Melo.

3 recordsLinked to original sources

arXiv2026

Foundation Models as Oracles for Refactoring Correctness Detection

Refactoring tools in popular Integrated Development Environments (IDEs) can introduce unintended behavioral changes or compilation errors, a persistent challenge that undermines developer trust in automated transformations. Traditional detection approaches rely on handcrafted preconditions, and static and dynamic analyses, yet remain limited in adaptability and can miss subtle correctness issues. This study examines the potential of foundation models to serve as oracles for detecting refactoring bugs in Java programs. We evaluate zero-shot prompting, without task-specific training, across 226 real refactoring bugs collected over more than a decade from widely used Java IDEs (IntelliJ-IDEA, Eclipse, and NetBeans), spanning 47 refactoring types. Our results indicate that foundation models can be effective for this task, although performance varies across models. In the first-run setting, GPT-OSS-20B achieved 80.5% accuracy, while GPT-5.4 reached 93.8%. We also evaluated other open-weight and proprietary models: Gemma-4-31B achieved the strongest result among open-weight models, and Gemini-3.1-Pro-Preview achieved the best overall result among all evaluated models. Metamorphic testing indicates that model predictions remain largely consistent under the tested semantics-preserving perturbations, but these results should be interpreted as robustness evidence rather than as evidence against memorization or data contamination. Beyond detection accuracy, foundation models can provide short explanations that may help support developer inspection, operate across refactoring types without explicitly encoded refactoring-specific rules, and may serve as lightweight triage aids in development workflows. Our findings suggest that foundation models can complement traditional refactoring checks by flagging suspicious transformations for developer inspection.

cs.SE↗

arXiv2025

RefModel: Detecting Refactorings using Foundation Models

Refactoring is a common software engineering practice that improves code quality without altering program behavior. Although tools like ReExtractor+, RefactoringMiner, and RefDiff have been developed to detect refactorings automatically, they rely on complex rule definitions and static analysis, making them difficult to extend and generalize to other programming languages. In this paper, we investigate the viability of using foundation models for refactoring detection, implemented in a tool named RefModel. We evaluate Phi4-14B, and Claude 3.5 Sonnet on a dataset of 858 single-operation transformations applied to artificially generated Java programs, covering widely-used refactoring types. We also extend our evaluation by including Gemini 2.5 Pro and o4-mini-high, assessing their performance on 44 real-world refactorings extracted from four open-source projects. These models are compared against RefactoringMiner, RefDiff, and ReExtractor+. RefModel is competitive with, and in some cases outperform, traditional tools. In real-world settings, Claude 3.5 Sonnet and Gemini 2.5 Pro jointly identified 97% of all refactorings, surpassing the best-performing static-analysis-based tools. The models showed encouraging generalization to Python and Golang. They provide natural language explanations and require only a single sentence to define each refactoring type.

cs.SE↗

arXiv2025

Agentic LMs: Hunting Down Test Smells

Test smells reduce test suite reliability and complicate maintenance. While many methods detect test smells, few support automated removal, and most rely on static analysis or machine learning. This study evaluates models with relatively small parameter counts - Llama-3.2-3B, Gemma-2-9B, DeepSeek-R1-14B, and Phi-4-14B - for their ability to detect and refactor test smells using agent-based workflows. We assess workflows with one, two, and four agents over 150 instances of 5 common smells from real-world Java projects. Our approach generalizes to Python, Golang, and JavaScript. All models detected nearly all instances, with Phi-4-14B achieving the best refactoring accuracy (pass@5 of 75.3%). Phi-4-14B with four-agents performed within 5% of proprietary LLMs (single-agent). Multi-agent setups outperformed single-agent ones in three of five smell types, though for Assertion Roulette, one agent sufficed. We submitted pull requests with Phi-4-14B-generated code to open-source projects and six were merged.

cs.SE↗