Cover Image

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ehsani, Ramtin, Pathak, Sakshi, Rawal, Shriya, Mujahid, Abdullah Al, Imran, Mia Mohammad, Chatterjee, Preetha
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

What Characteristics Make ChatGPT Effective for Software Issue Resolution? An Empirical Study of Task, Project, and Conversational Signals in GitHub Issues
by: Ehsani, Ramtin, et al.
Published: (2025)

Incivility in Open Source Projects: A Comprehensive Annotated Dataset of Locked GitHub Issue Threads
by: Ehsani, Ramtin, et al.
Published: (2024)

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

Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution
by: Ehsani, Ramtin, et al.
Published: (2025)

Toxicity Ahead: Forecasting Conversational Derailment on GitHub
by: Imran, Mia Mohammad, et al.
Published: (2025)

Understanding and Predicting Derailment in Toxic Conversations on GitHub
by: Imran, Mia Mohammad, et al.
Published: (2025)

Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub
by: Siddiq, Mohammed Latif, et al.
Published: (2026)

Do LLMs Suggest Consistent Identifiers? An Empirical Study on GitHub Pull Requests
by: Rodrigues, Julyanara
Published: (2025)

GitHub Actions: The Impact on the Pull Request Process
by: Wessel, Mairieli, et al.
Published: (2022)

Bugdar: AI-Augmented Secure Code Review for GitHub Pull Requests
by: Naulty, John, et al.
Published: (2025)

On the Footprints of Reviewer Bots Feedback on Agentic Pull Requests in OSS GitHub Repositories
by: Fatima, Syeda Kaneez, et al.
Published: (2026)

An Empirical Study on Developers Shared Conversations with ChatGPT in GitHub Pull Requests and Issues
by: Hao, Huizi, et al.
Published: (2024)

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

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

What Developers Ask to ChatGPT in GitHub Pull Requests? an Exploratory Study
by: Silva, Julyanara R., et al.
Published: (2025)

Analyzing Toxicity in Open Source Software Communications Using Psycholinguistics and Moral Foundations Theory
by: Ehsani, Ramtin, et al.
Published: (2024)

LLM-Enabled Open-Source Systems in the Wild: An Empirical Study of Vulnerabilities in GitHub Security Advisories
by: Shifat, Fariha Tanjim, et al.
Published: (2026)

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

Analyzing GitHub Issues and Pull Requests in nf-core Pipelines: Insights into nf-core Pipeline Repositories
by: Alam, Khairul, et al.
Published: (2026)

"TODO: Fix the Mess Gemini Created": Towards Understanding GenAI-Induced Self-Admitted Technical Debt
by: Mujahid, Abdullah Al, et al.
Published: (2026)

Hierarchical Knowledge Injection for Improving LLM-based Program Repair
by: Ehsani, Ramtin, et al.
Published: (2025)

Where Is Self-admitted Code Generated by Large Language Models on GitHub?
by: Yu, Xiao, et al.
Published: (2024)

Fingerprinting AI Coding Agents on GitHub
by: Ghaleb, Taher A.
Published: (2026)

The Landscape of Toxicity: An Empirical Investigation of Toxicity on GitHub
by: Sarker, Jaydeb, et al.
Published: (2025)

An Empirical Study of the Evolution of GitHub Actions Workflows
by: Mazrae, Pooya Rostami, et al.
Published: (2026)

Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study
by: Fu, Yujia, et al.
Published: (2023)

Imago GitHub training
by: Elsey, Jonathan
Published: (2026)

GitHub Copilot: the perfect Code compLeeter?
by: Siroš, Ilja, et al.
Published: (2024)

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

GitHub Proxy Server: A tool for supporting massive data collection on GitHub
by: Borges, Hudson Silva, et al.
Published: (2025)

LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN prover
by: Wu, Zijian, et al.
Published: (2024)

Exploring User Privacy Awareness on GitHub: An Empirical Study
by: Alfieri, Costanza, et al.
Published: (2024)

Towards A Sustainable Future for Peer Review in Software Engineering
by: Parra, Esteban, et al.
Published: (2026)

Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions
by: Wang, Shenao, et al.
Published: (2026)

Is GitHub's Copilot as Bad as Humans at Introducing Vulnerabilities in Code?
by: Asare, Owura, et al.
Published: (2022)

Immersion in the GitHub Universe: Scaling Coding Agents to Mastery
by: Zhao, Jiale, et al.
Published: (2026)

Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
by: Cipollone, Daniele, et al.
Published: (2025)

Policy-driven Software Bill of Materials on GitHub: An Empirical Study
by: Novikov, Oleksii, et al.
Published: (2025)

Development and Evolution of Xtext-based DSLs on GitHub: An Empirical Investigation
by: Zhang, Weixing, et al.
Published: (2025)

An Empirical Study of ChatGPT-Related Projects and Their Issues on GitHub
by: Lin, Zheng, et al.
Published: (2024)