Copertina

Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gong, Jingzhi, Pinna, Giovanni, Bian, Yixin, Zhang, Jie M.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Software Engineering Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance
di: Pinna, Giovanni, et al.
Pubblicazione: (2026)

When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requests
di: Nachuma, Costain, et al.
Pubblicazione: (2026)

GA4GC: Greener Agent for Greener Code via Multi-Objective Configuration Optimization
di: Gong, Jingzhi, et al.
Pubblicazione: (2025)

How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses
di: Watanabe, Kan, et al.
Pubblicazione: (2026)

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
di: Ehsani, Ramtin, et al.
Pubblicazione: (2026)

SWE-PRBench: Benchmarking AI Code Review Quality Against Pull Request Feedback
di: Kumar, Deepak
Pubblicazione: (2026)

Pull Requests as a Training Signal for Repo-Level Code Editing
di: Zhu, Qinglin, et al.
Pubblicazione: (2026)

CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detection
di: Zhang, Qingyu, et al.
Pubblicazione: (2025)

More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests
di: Huang, Haoming, et al.
Pubblicazione: (2026)

Why Are AI Agent Involved Pull Requests (Fix-Related) Remain Unmerged? An Empirical Study
di: Alam, Khairul, et al.
Pubblicazione: (2026)

A Study of Library Usage in Agent-Authored Pull Requests
di: Twist, Lukas, et al.
Pubblicazione: (2025)

How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests
di: Ogenrwot, Daniel, et al.
Pubblicazione: (2026)

Quality and Security Signals in AI-Generated Python Refactoring Pull Requests
di: Almukhtar, Mohamed, et al.
Pubblicazione: (2026)

Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents Approach
di: Ashiga, Mari, et al.
Pubblicazione: (2025)

Multi-line AI-assisted Code Authoring
di: Dunay, Omer, et al.
Pubblicazione: (2024)

Pushing the Boundary: Specialising Deep Configuration Performance Learning
di: Gong, Jingzhi
Pubblicazione: (2024)

MELT: Mining Effective Lightweight Transformations from Pull Requests
di: Ramos, Daniel, et al.
Pubblicazione: (2023)

On Unified Prompt Tuning for Request Quality Assurance in Public Code Review
di: Chen, Xinyu, et al.
Pubblicazione: (2024)

MarsCode Agent: AI-native Automated Bug Fixing
di: Liu, Yizhou, et al.
Pubblicazione: (2024)

AIDev: Studying AI Coding Agents on GitHub
di: Li, Hao, et al.
Pubblicazione: (2026)

Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective
di: Gong, Jingzhi, et al.
Pubblicazione: (2025)

Knowledge-Guided Prompt Learning for Request Quality Assurance in Public Code Review
di: Li, Lin, et al.
Pubblicazione: (2024)

Collaborator or Assistant? How AI Coding Agents Partition Work Across Pull Request Lifecycles
di: Jo, Young, et al.
Pubblicazione: (2026)

Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models
di: Wang, Yanlin, et al.
Pubblicazione: (2024)

AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation
di: Murali, Vijayaraghavan, et al.
Pubblicazione: (2023)

On Wasted Contributions: Understanding the Dynamics of Contributor-Abandoned Pull Requests
di: Khatoonabadi, SayedHassan, et al.
Pubblicazione: (2021)

Predicting the First Response Latency of Maintainers and Contributors in Pull Requests
di: Khatoonabadi, SayedHassan, et al.
Pubblicazione: (2023)

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

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
di: Guo, Chengquan, et al.
Pubblicazione: (2024)

On Assessing the Relevance of Code Reviews Authored by Generative Models
di: Heumüller, Robert, et al.
Pubblicazione: (2025)

On The Impact of Merge Request Deviations on Code Review Practices
di: Kansab, Samah, et al.
Pubblicazione: (2025)

AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub
di: Ogenrwot, Daniel, et al.
Pubblicazione: (2026)

Code Review Agent Benchmark
di: Zhang, Yuntong, et al.
Pubblicazione: (2026)

Formal Architecture Descriptors as Navigation Primitives for AI Coding Agents
di: Jin, Ruoqi
Pubblicazione: (2026)

Predicting Software Performance with Divide-and-Learn
di: Gong, Jingzhi, et al.
Pubblicazione: (2023)

Dually Hierarchical Drift Adaptation for Online Configuration Performance Learning
di: Xiang, Zezhen, et al.
Pubblicazione: (2025)

Dividable Configuration Performance Learning
di: Gong, Jingzhi, et al.
Pubblicazione: (2024)

Accuracy Can Lie: On the Impact of Surrogate Model in Configuration Tuning
di: Chen, Pengzhou, et al.
Pubblicazione: (2025)

From Industry Claims to Empirical Reality: An Empirical Study of Code Review Agents in Pull Requests
di: Chowdhury, Kowshik, et al.
Pubblicazione: (2026)

AI-Assisted Assessment of Coding Practices in Modern Code Review
di: Vijayvergiya, Manushree, et al.
Pubblicazione: (2024)