Imagen de Portada

Static Analysis as a Feedback Loop: Enhancing LLM-Generated Code Beyond Correctness

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Blyth, Scott, Licorish, Sherlock A., Treude, Christoph, Wagner, Markus
Formato:	Preprint
Publicado:	2025
Materias:	Software Engineering
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Creative and Correct: Requesting Diverse Code Solutions from AI Foundation Models
por: Blyth, Scott, et al.
Publicado: (2024)

Optimizing Large Language Model Hyperparameters for Code Generation
por: Arora, Chetan, et al.
Publicado: (2024)

Enhancing Source Code Representations for Deep Learning with Static Analysis
por: Guan, Xueting, et al.
Publicado: (2024)

Taking a Closer Look at Warnings Generated by PMD and SonarQube, their Rules and Compliance to Established Coding Standards
por: Deshapriya, Lakmal, et al.
Publicado: (2026)

On the need to perform comprehensive evaluations of automated program repair benchmarks: Sorald case study
por: Liyanage, Sumudu, et al.
Publicado: (2025)

Understanding the Effect of Agile Practice Quality on Software Product Quality
por: Licorish, Sherlock Anthony
Publicado: (2024)

An Empirical Study of Static Analysis Tools for Secure Code Review
por: Charoenwet, Wachiraphan, et al.
Publicado: (2024)

Information-Theoretic Detection of Unusual Source Code Changes
por: Torres, Adriano, et al.
Publicado: (2025)

The Future of Software Engineering Conferences: A New Zealand Perspective
por: Blincoe, Kelly, et al.
Publicado: (2026)

A Pilot Study on Detecting Software Design Patterns with Large Language Models: An Empirical Evaluation
por: Chowdhury, Oishik, et al.
Publicado: (2026)

At What Cost? Software Developers' Well-Being in the Age of GenAI
por: Guizani, Mariam, et al.
Publicado: (2026)

Comparing Human and LLM Generated Code: The Jury is Still Out!
por: Licorish, Sherlock A., et al.
Publicado: (2025)

Qualitative Data Analysis in Software Engineering: Techniques and Teaching Insights
por: Treude, Christoph
Publicado: (2024)

Geographic Variation in Stack Overflow Code Quality: Evidence from a Cross-Regional Study of Coding Practices
por: Zolduoarrati, Elijah, et al.
Publicado: (2026)

The Shift from Writing to Pruning Software: A Bonsai-Inspired IDE for Reshaping AI Generated Code
por: Kula, Raula Gaikovina, et al.
Publicado: (2025)

Socialz: Multi-Feature Social Fuzz Testing
por: Zanartu, Francisco, et al.
Publicado: (2023)

Predictive Analytics for Collaborators Answers, Code Quality, and Dropout on Stack Overflow
por: Zolduoarrati, Elijah, et al.
Publicado: (2025)

Enhancing Neural Code Representation with Additional Context
por: Nguyen, Huy, et al.
Publicado: (2025)

Deterministic vs. Probabilistic Summarisation: An Empirical Trade-off Study in Design Pattern Centric Java Code
por: Nazar, Najam, et al.
Publicado: (2026)

Do Comments and Expertise Still Matter? An Experiment on Programmers' Adoption of AI-Generated JavaScript Code
por: Li, Changwen, et al.
Publicado: (2025)

Enhancing Code Review through Fuzzing and Likely Invariants
por: Charoenwet, Wachiraphan, et al.
Publicado: (2025)

Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap
por: Treude, Christoph
Publicado: (2026)

Using a Feedback Loop for LLM-based Infrastructure as Code Generation
por: Palavalli, Mayur Amarnath, et al.
Publicado: (2024)

ModARO: A Modular Approach to Architecture Reconstruction of Distributed Microservice Codebases
por: Manglaras, Oscar, et al.
Publicado: (2026)

Distributed Architecture Reconstruction of Polyglot and Multi-Repository Microservice Projects
por: Manglaras, Oscar, et al.
Publicado: (2026)

Towards the First Code Contribution: Processes and Information Needs
por: Treude, Christoph, et al.
Publicado: (2024)

Why Do You Contribute to Stack Overflow? Understanding Cross-Cultural Motivations and Usage Patterns before the Age of LLMs
por: Licorish, Sherlock A., et al.
Publicado: (2026)

Encoding Version History Context for Better Code Representation
por: Nguyen, Huy, et al.
Publicado: (2024)

Integrating Static Code Analysis Toolchains
por: Kern, Matthias, et al.
Publicado: (2024)

The Role of Code Proficiency in the Era of Generative AI
por: Robles, Gregorio, et al.
Publicado: (2024)

Automated Code Review Assignments: An Alternative Perspective of Code Ownership on GitHub
por: Lulla, Jai Lal, et al.
Publicado: (2025)

LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead
por: He, Junda, et al.
Publicado: (2024)

Toward Effective Secure Code Reviews: An Empirical Study of Security-Related Coding Weaknesses
por: Charoenwet, Wachiraphan, et al.
Publicado: (2023)

Improving LLM-Based Go Code Review through Issue-List Generation and Context Augmentation
por: Sun, Kexin, et al.
Publicado: (2026)

Static Code Analysis with CodeChecker
por: Horvath, Gabor, et al.
Publicado: (2024)

Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis
por: Dolcetti, Greta, et al.
Publicado: (2024)

How Fair is Software Fairness Testing?
por: Barcomb, Ann, et al.
Publicado: (2026)

Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
por: Liu, Fang, et al.
Publicado: (2024)

Improving Automated Code Reviews: Learning from Experience
por: Lin, Hong Yi, et al.
Publicado: (2024)

GenAI Is No Silver Bullet for Qualitative Research in Software Engineering
por: Ernst, Neil A., et al.
Publicado: (2026)