Image de couverture de livre

Code Change Characteristics and Description Alignment: A Comparative Study of Agentic versus Human Pull Requests

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pham, Dung, Ghaleb, Taher A.
Format:	Preprint
Publié:	2026
Sujets:	Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fingerprinting AI Coding Agents on GitHub
par: Ghaleb, Taher A.
Publié: (2026)

On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
par: Watanabe, Miku, et autres
Publié: (2025)

How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses
par: Watanabe, Kan, et autres
Publié: (2026)

The Value of Effective Pull Request Description
par: Pirouzkhah, Shirin, et autres
Publié: (2026)

Do Autonomous Agents Contribute Test Code? A Study of Tests in Agentic Pull Requests
par: Haque, Sabrina, et autres
Publié: (2026)

Let's Make Every Pull Request Meaningful: An Empirical Analysis of Developer and Agentic Pull Requests
par: Yoshioka, Haruhiko, et autres
Publié: (2026)

How Do Developers Use Code Suggestions in Pull Request Reviews?
par: Bouraffa, Abir, et autres
Publié: (2025)

Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study
par: Peralta, Sien Reeve O., et autres
Publié: (2026)

When AI Agents Touch CI/CD Configurations: Frequency and Success
par: Ghaleb, Taher A.
Publié: (2026)

Human-Agent versus Human Pull Requests: A Testing-Focused Characterization and Comparison
par: Milanese, Roberto, et autres
Publié: (2026)

Can LLMs Write CI? A Study on Automatic Generation of GitHub Actions Configurations
par: Ghaleb, Taher A., et autres
Publié: (2025)

How Compliant Are GitHub Actions Workflows? A Checklist-Based Study with LLM-Assisted Auditing
par: Abrokwah, Edward, et autres
Publié: (2026)

An Empirical Study of Complexity, Heterogeneity, and Compliance of GitHub Actions Workflows
par: Abrokwah, Edward, et autres
Publié: (2025)

From First Use to Final Commit: Studying the Evolution of Multi-CI Service Adoption
par: Chopra, Nitika, et autres
Publié: (2025)

Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance
par: Pinna, Giovanni, et autres
Publié: (2026)

Empirical Analysis of Pull Requests for Google Summer of Code
par: Popoola, Saheed
Publié: (2024)

Mapping GitHub Sponsorships: A Longitudinal Observatory for Open-Source Sustainability
par: Hiltz, Rylan, et autres
Publié: (2026)

Generative AI for Pull Request Descriptions: Adoption, Impact, and Developer Interventions
par: Xiao, Tao, et autres
Publié: (2024)

Evaluating the Impact of Data Cleaning on the Quality of Generated Pull Request Descriptions
par: Tire, Kutay, et autres
Publié: (2025)

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
par: Ehsani, Ramtin, et autres
Publié: (2026)

CI/CD Configuration Practices in Open-Source Android Apps: An Empirical Study
par: Ghaleb, Taher A., et autres
Publié: (2024)

Role of CI Adoption in Mobile App Success: An Empirical Study of Open-Source Android Projects
par: Zhou, Xiaoxin, et autres
Publié: (2026)

A Vision for Context-Aware CI Adoption Decisions
par: Alaini, Osamah H., et autres
Publié: (2026)

A Comprehensive Multi-Vocal Empirical Study of ML Cloud Service Misuses
par: Amor, Hadil Ben, et autres
Publié: (2025)

How Do Agentic AI Systems Deal With Software Energy Concerns? A Pull Request-Based Study
par: Mitul, Tanjum Motin, et autres
Publié: (2025)

A Study of Library Usage in Agent-Authored Pull Requests
par: Twist, Lukas, et autres
Publié: (2025)

On the Footprints of Reviewer Bots Feedback on Agentic Pull Requests in OSS GitHub Repositories
par: Fatima, Syeda Kaneez, et autres
Publié: (2026)

From Industry Claims to Empirical Reality: An Empirical Study of Code Review Agents in Pull Requests
par: Chowdhury, Kowshik, et autres
Publié: (2026)

Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub
par: Siddiq, Mohammed Latif, et autres
Publié: (2026)

CIgrate: Automating CI Service Migration with Large Language Models
par: Hossain, Md Nazmul, et autres
Publié: (2025)

Quality Gatekeepers: Investigating the Effects ofCode Review Bots on Pull Request Activities
par: Wessel, Mairieli, et autres
Publié: (2021)

Change And Cover: Last-Mile, Pull Request-Based Regression Test Augmentation
par: Zhou, Zitong, et autres
Publié: (2026)

Security Debt in Practice: Nuanced Insights from Practitioners
par: Boufaied, Chaima, et autres
Publié: (2025)

The Promise and Reality of Continuous Integration Caching: An Empirical Study of Travis CI Builds
par: Ghaleb, Taher A., et autres
Publié: (2026)

GitHub Actions: The Impact on the Pull Request Process
par: Wessel, Mairieli, et autres
Publié: (2022)

Self-Admitted Technical Debt in LLM Software: An Empirical Comparison with ML and Non-ML Software
par: Selvanayagam, Niruthiha, et autres
Publié: (2026)

Android Instrumentation Testing in Continuous Integration: Practices, Patterns, and Performance
par: Parsazadeh, Hamid, et autres
Publié: (2026)

LTM: Scalable and Black-box Similarity-based Test Suite Minimization based on Language Models
par: Pan, Rongqi, et autres
Publié: (2023)

How Do Agentic AI Systems Address Performance Optimizations? A BERTopic-Based Analysis of Pull Requests
par: Opu, Md Nahidul Islam, et autres
Publié: (2025)

Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests
par: Gong, Jingzhi, et autres
Publié: (2026)