Cover Image

Agentic Refactoring: An Empirical Study of AI Coding Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Horikawa, Kosei, Li, Hao, Kashiwa, Yutaro, Adams, Bram, Iida, Hajimu, Hassan, Ahmed E.
Format:	Preprint
Published:	2025
Subjects:	Software Engineering D.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality
by: Zhong, Suzhen, et al.
Published: (2025)

Do AI Agents Really Improve Code Readability?
by: Horikawa, Kyogo, et al.
Published: (2026)

Testing with AI Agents: An Empirical Study of Test Generation Frequency, Quality, and Coverage
by: Yoshimoto, Suzuka, et al.
Published: (2026)

Diagnosing Refactoring Dangers
by: Brinksma, Wouter, et al.
Published: (2024)

Recommending Variable Names for Extract Local Variable Refactorings
by: Wang, Taiming, et al.
Published: (2025)

On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
by: Watanabe, Miku, et al.
Published: (2025)

Agent READMEs: An Empirical Study of Context Files for Agentic Coding
by: Chatlatanagulchai, Worawalan, et al.
Published: (2025)

LLM-based vs. Search-based Merge Conflict Resolution: An Empirical Study of Competing Paradigms
by: Junior, Heleno de Souza Campos, et al.
Published: (2026)

When Code Smells Meet ML: On the Lifecycle of ML-specific Code Smells in ML-enabled Systems
by: Recupito, Gilberto, et al.
Published: (2024)

Understanding Self-Admitted Technical Debt in Test Code: An Empirical Study
by: Nakamura, Ibuki, et al.
Published: (2025)

Refactoring-Aware Patch Integration Across Structurally Divergent Java Forks
by: Ogenrwot, Daniel, et al.
Published: (2025)

Early-Stage Prediction of Review Effort in AI-Generated Pull Requests
by: Minh, Dao Sy Duy, et al.
Published: (2026)

What to Cut? Predicting Unnecessary Methods in Agentic Code Generation
by: Watanabe, Kan, et al.
Published: (2026)

LLMs as Idiomatic Decompilers: Recovering High-Level Code from x86-64 Assembly for Dart
by: Abualazm, Raafat, et al.
Published: (2026)

A Preliminary Study on Self-Contained Libraries in the NPM Ecosystem
by: Jaisri, Pongchai, et al.
Published: (2024)

When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context
by: Weng, Haojun, et al.
Published: (2026)

The Upper Bound of Information Diffusion in Code Review
by: Dorner, Michael, et al.
Published: (2023)

Toward Architecture-Aware Evaluation Metrics for LLM Agents
by: Souza, Débora, et al.
Published: (2026)

Towards Identifying Code Proficiency through the Analysis of Python Textbooks
by: Rojpaisarnkit, Ruksit, et al.
Published: (2024)

AgentModernize: Preserving Business Logic in Legacy Modernization with Multi-Agent LLMs and Behavioral Specification Graphs
by: Ahmed, Sheikh Nazib, et al.
Published: (2026)

On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code
by: Chatlatanagulchai, Worawalan, et al.
Published: (2025)

Automated Detection of Algorithm Debt in Deep Learning Frameworks: An Empirical Study
by: Simon, Emmanuel Iko-Ojo, et al.
Published: (2024)

Migrating Esope to Fortran 2008 using model transformations
by: Sow, Younoussa, et al.
Published: (2026)

Choosing the Right Git Workflow: A Comparative Analysis of Trunk-based vs. Branch-based Approaches
by: Lopes, Pedro, et al.
Published: (2025)

A Story About Cohesion and Separation: Label-Free Metric for Log Parser Evaluation
by: Qin, Qiaolin, et al.
Published: (2025)

Providing Information About Implemented Algorithms Improves Program Comprehension: A Controlled Experiment
by: Neumüller, Denis, et al.
Published: (2025)

Beyond Greenfield: The D3 Framework for AI-Driven Productivity in Brownfield Engineering
by: Sharma, Krishna Kumaar
Published: (2025)

Lore: Repurposing Git Commit Messages as a Structured Knowledge Protocol for AI Coding Agents
by: Stetsenko, Ivan
Published: (2026)

Prompt Engineering Strategies for LLM-based Qualitative Coding of Psychological Safety in Software Engineering Communities: A Controlled Empirical Study
by: Alshaikh, Moaath, et al.
Published: (2026)

To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study
by: Sawada, Shota, et al.
Published: (2026)

Automated Code Review Using Large Language Models at Ericsson: An Experience Report
by: Ramesh, Shweta, et al.
Published: (2025)

Learning Software Bug Reports: A Systematic Literature Review
by: Long, Guoming, et al.
Published: (2025)

Empirical Investigation of the Relationship Between Design Smells and Role Stereotypes
by: Ogenrwot, Daniel, et al.
Published: (2024)

Energy-Aware Decision Making in Software Stack Upgrades
by: Stocker, Mirko, et al.
Published: (2026)

Reliability of AI Bots Footprints in GitHub Actions CI/CD Workflows
by: Shah, Syed Muhammad Ashhar, et al.
Published: (2026)

Automated Bug Triaging using Instruction-Tuned Large Language Models
by: Kiashemshaki, Kiana, et al.
Published: (2025)

SPViz: A DSL-Driven Approach for Software Project Visualization Tooling
by: Rentz, Niklas, et al.
Published: (2024)

Characterising Contributions that Coincide with Vulnerability Mitigation in NPM Libraries
by: Rojpaisarnkit, Ruksit, et al.
Published: (2024)

Interoperability From Kieker to OpenTelemetry: Demonstrated as Export to ExplorViz
by: Reichelt, David Georg, et al.
Published: (2024)

Does Programming Language Matter? An Empirical Study of Fuzzing Bug Detection
by: Shirai, Tatsuya, et al.
Published: (2026)