MétaCan
Menu
← Back to cohort

LLM-Powered Code Quality Bot: Automating Refactoring in CI/CD

2025· article· W7125592731 on OpenAlexaff
Akram Adem, Glaucia Melo

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicSoftware Engineering Research
Canadian institutionsToronto Metropolitan University
Fundersnot available
KeywordsCode refactoringCode (set theory)Code smellPipeline (software)Focus (optics)SoftwareStatic program analysisSoftware qualityQuality (philosophy)

Abstract

fetched live from OpenAlex

Code quality issues, such as code smells and minor bugs, consume valuable developer time and can slow down software delivery pipelines. This poster presents SonaRefactor, an AI-assisted CI/CD pipeline that merges SonarCloud static analysis with Gemini LLM to automatically summarize flagged issues and propose safe, minimal code fixes. When a pull request is opened, the bot automatically detects issues, explains them in context, and generates a minimal safe autofix that is committed back as a new pull request. This work demonstrates how large language models can act as hands-on teammates in software development pipelines, offloading repetitive refactoring tasks so developers can focus on more complex and creative aspects of software engineering. Our tool minimizes developer interruption by enforcing conservative, auditable changes that reduce friction in the review process, without compromising safety or autonomy.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.021
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.009
Threshold uncertainty score0.030

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.021
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.001
Science and technology studies0.0010.001
Scholarly communication0.0020.003
Open science0.0020.003
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0090.006

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.048
GPT teacher head0.374
Teacher spread0.326 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicSoftware Engineering Research→French-language works237,207→