This paper performs a broad analysis on the refactoring capabilities of small open-weight language models (SLMs) by evaluating 12 models on 3453 Python programs and indicates that current open SLMs can support refactoring tasks, especially larger ones with reasoning capabilities, but they are best used with human oversight.
Results indicate that static checks and test-guided, context-aware agentic repair can increase the reliability of LLM-generated refactorings, bringing them closer to practical integration within developer workflows.
Jonathan Cordeiro, Shayan Noei, Ying Zou· 1 citation
This work proposes an approach based on a foundation model oracle that analyzes git-style diffs to identify behavioral changes introduced by Python refactorings and uncovered 13 distinct bugs among the seven refactoring types studied.
Jonhnanthan Oliveira, Rohit Gheyi, Márcio Ribeiro et al.· 0 citations
The findings show that, while LLMs achieve promising results, they struggle with harder problems and with programming languages that have fewer available resources for training, and they often fail due to fundamental and easily avoidable errors that underscore the unreliability of automatically generated code.
Rodrigo Pato Nogueira, Marco Vieira, João R. Campos· Empirical Software Engineeri...· 1 citation
Investigating LLMs as metric-driven refactoring assistants rather than code generators suggests that while LLMs are valuable assistants for structural improvement, their interventions require careful monitoring to avoid unintended trade-offs.
Tindwende Thierry Sawadogo, Fadel Touré· International Conference on...· 0 citations
A comprehensive taxonomy of data-centric refactoring strategies is introduced, their application across ML-driven software projects is investigated, and their impact on model accuracy, robustness, maintainability, and reproducibility is evaluated.
Fatou Diop· International Journal of Art...· 0 citations
It is observed that generated code often omits basic input validation or memory-safety checks, which can lead to overflows, resource exhaustion, or other reliability/security issues, and even the largest models frequently make simple mistakes.
Rodrigo Pato Nogueira, Marco Vieira, João R. Campos· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
