Article

Investigating the Refactoring Capabilities of Small Open-Weight Language Models

2026-03-04

Abstract excerpt

Refactoring is essential for developing maintainable software. Using Large Language Models in software engineering is widespread, but compared to well-established domains such as code generation, reliable refactoring is still relatively underexplored. In this paper, we perform a broad analysis on the refactoring capabilities of small open-weight language models (SLMs) by evaluating 12 models on 3,453 Python progra...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: de7fd473-f2dd-5fcb-9b5a-6c688843680b
DOI: 10.20944/preprints202603.0295.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Investigating the Refactoring Capabilities of Small Open-Weight Language ModelsDOI 10.20944/preprints202603.0295.v1Read

Self-Debugging AI: A Comprehensive Analysis of Claude 4.1 Sonnet's Code Generation and Error Resolution CapabilitiesSemantic proximity Read

Variable Naming Impact on AI Code Completion: An Empirical StudySemantic proximity Read

A Systematic Literature Review on Generative AI in Software Engineering: Code Generation and RefactoringSemantic proximity Read

Intent-Driven Code Synthesis: Redefining Software Development with TransformersSemantic proximity Read

Reassessing One-Round Test-Time Refinement for Code GenerationSemantic proximity Read

Benchmarking Large Language Models for Data Pipeline Code Generation and ExecutionSemantic proximity Read

Reflective Reasoning System: Inference-Time Self-Diagnosis and Self-Correction for Large Reasoning ModelsSemantic proximity Read

A Reference Framework for Empirical Studies on LLM-Based Code Generation: A Review-Grounded SynthesisSemantic proximity Read

Who Broke the Pipeline? Traceability andAccountability in Multi-Agent LLM SoftwareEngineering PipelinesSemantic proximity Read

Investigating Reproducibility Challenges in LLM Bugfixing on the HumanEvalFix BenchmarkSemantic proximity Read

LLM-Based Test Case Generation from Natural-Language Requirements: A Verified Multi-Domain Empirical Study with Symbolic Mutation IndicatorsSemantic proximity Read

Behavioral Augmentation of UML Class Diagrams: An Empirical Study of Large Language Models for Method GenerationSemantic proximity Read