Cover Image

Why Agentic-PRs Get Rejected: A Comparative Study of Coding Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nakashima, Sota, Ishimoto, Yuta, Kondo, Masanari, Mclntosh, Shane, Kamei, Yasutaka
Format:	Preprint
Published:	2026
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How Far Have LLMs Come Toward Automated SATD Taxonomy Construction?
by: Nakashima, Sota, et al.
Published: (2025)

Toward Linking Declined Proposals and Source Code: An Exploratory Study on the Go Repository
by: Nakashima, Sota, et al.
Published: (2026)

Leveraging Mutation Analysis for LLM-based Repair of Quantum Programs
by: Yoshida, Chihiro, et al.
Published: (2026)

Evaluating Mutation-based Fault Localization for Quantum Programs
by: Ishimoto, Yuta, et al.
Published: (2025)

An empirical study on declined proposals: why are these proposals declined?
by: Kondo, Masanari, et al.
Published: (2025)

Leveraging Language Models for Log Statement Generation in Multilingual Scenarios: How Far Are We?
by: Kusama, Kazuki, et al.
Published: (2026)

How Small is Enough? Empirical Evidence of Quantized Small Language Models for Automated Program Repair
by: Kusama, Kazuki, et al.
Published: (2025)

"Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution
by: Tian, Zhao, et al.
Published: (2026)

An Empirical Study of Token-based Micro Commits
by: Kondo, Masanari, et al.
Published: (2024)

AILINKPREVIEWER: Enhancing Code Reviews with LLM-Powered Link Previews
by: Trakoolgerntong, Panya, et al.
Published: (2025)

Exploring the Effect of Multiple Natural Languages on Code Suggestion Using GitHub Copilot
by: Koyanagi, Kei, et al.
Published: (2024)

OSS Myths and Facts
by: Iimura, Yukako, et al.
Published: (2024)

Myth: The loss of core developers is a critical issue for OSS communities
by: Nourry, Olivier, et al.
Published: (2024)

Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study
by: Peralta, Sien Reeve O., et al.
Published: (2026)

Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs
by: Ferdous, K M, et al.
Published: (2026)

Cross-Project Flakiness: A Case Study of the OpenStack Ecosystem
by: Xiao, Tao, et al.
Published: (2026)

Deciphering WONTFIX: A Mixed-Method Study on Why GitHub Issues Get Rejected
by: Curtis, J. Alexander, et al.
Published: (2025)

A Preliminary Study of Large Language Models for Multilingual Vulnerability Detection
by: Yu, Junji, et al.
Published: (2025)

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

Large Language Models for Equivalent Mutant Detection: How Far Are We?
by: Tian, Zhao, et al.
Published: (2024)

Large-Scale Empirical Analysis of Continuous Fuzzing: Insights from 1 Million Fuzzing Sessions
by: Shirai, Tatsuya, et al.
Published: (2025)

Code Change Characteristics and Description Alignment: A Comparative Study of Agentic versus Human Pull Requests
by: Pham, Dung, et al.
Published: (2026)

Do Autonomous Agents Contribute Test Code? A Study of Tests in Agentic Pull Requests
by: Haque, Sabrina, et al.
Published: (2026)

Agentic Much? Adoption of Coding Agents on GitHub
by: Robbes, Romain, et al.
Published: (2026)

Evaluating Large Language Models for Multilingual Vulnerability Detection at Dual Granularities
by: Shu, Honglin, et al.
Published: (2025)

On the Evaluation of Large Language Models in Multilingual Vulnerability Repair
by: wang, Dong, et al.
Published: (2025)

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

Agentic Refactoring: An Empirical Study of AI Coding Agents
by: Horikawa, Kosei, et al.
Published: (2025)

Configuring Agentic AI Coding Tools: An Exploratory Study
by: Galster, Matthias, et al.
Published: (2026)

Mind the Gap: A Decade-Scale Empirical Study of Multi-Stakeholder Dynamics in VR Ecosystem
by: Lu, Yijun, 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)

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

Agentic LLMs for REST API Test Amplification: A Comparative Study Across Cloud Applications
by: Besjes, Jarne, et al.
Published: (2025)

A Dataset of Agentic AI Coding Tool Configurations
by: Galster, Matthias, et al.
Published: (2026)

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

Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code
by: Kim, Myeongsoo, et al.
Published: (2026)

Human or LLM? A Comparative Study on Accessible Code Generation Capability
by: Suh, Hyunjae, et al.
Published: (2025)

OpenGame: Open Agentic Coding for Games
by: Jiang, Yilei, et al.
Published: (2026)

Human-AI Synergy in Agentic Code Review
by: Zhong, Suzhen, et al.
Published: (2026)

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