Cover Image

Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ferdous, K M, Banik, Dipayan, Chowdhury, Kowshik, Shamim, Shazibul Islam
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

Breaking the Dependency Chaos: A Constraint-Driven Python Dependency Resolution Strategy with Selective LLM Imputation
by: Chowdhury, Kowshik, et al.
Published: (2026)

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

DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder
by: Zhang, Jiaran, et al.
Published: (2026)

Why Agentic-PRs Get Rejected: A Comparative Study of Coding Agents
by: Nakashima, Sota, et al.
Published: (2026)

o3-mini vs DeepSeek-R1: Which One is Safer?
by: Arrieta, Aitor, et al.
Published: (2025)

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

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches
by: Mazur, Lukasz, et al.
Published: (2025)

ChatGPT vs. DeepSeek: A Comparative Study on AI-Based Code Generation
by: Manik, Md Motaleb Hossen
Published: (2025)

Better Python Programming for all: With the focus on Maintainability
by: Shivashankar, Karthik, et al.
Published: (2024)

Evaluating Large Language Models for Functional and Maintainable Code in Industrial Settings: A Case Study at ASML
by: Mundhra, Yash, et al.
Published: (2025)

LLM-Based Approach for Enhancing Maintainability of Automotive Architectures
by: Petrovic, Nenad, et al.
Published: (2025)

Maintainability Challenges in ML: A Systematic Literature Review
by: Shivashankar, Karthik, et al.
Published: (2024)

Analysis of LLMs vs Human Experts in Requirements Engineering
by: Hymel, Cory, et al.
Published: (2025)

Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
by: Sapkota, Ranjan, et al.
Published: (2025)

Agentic Frameworks for Reasoning Tasks: An Empirical Study
by: Rasheed, Zeeshan, et al.
Published: (2026)

Beyond Human-Readable: Rethinking Software Engineering Conventions for the Agentic Development Era
by: Ustynov, Dmytro
Published: (2026)

Needle in the Repo: A Benchmark for Maintainability in AI-Generated Repository Edits
by: Zhu, Haichao, et al.
Published: (2026)

Evaluating the Effectiveness of LLMs in Fixing Maintainability Issues in Real-World Projects
by: Nunes, Henrique, et al.
Published: (2025)

A Note on Code Quality Score: LLMs for Maintainable Large Codebases
by: Wong, Sherman, et al.
Published: (2025)

Echoes of AI: Investigating the Downstream Effects of AI Assistants on Software Maintainability
by: Borg, Markus, et al.
Published: (2025)

Willful Disobedience: Automatically Detecting Failures in Agentic Traces
by: Sharma, Reshabh K, et al.
Published: (2026)

Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development
by: Casserini, Matteo, et al.
Published: (2026)

Raw Pointer Rewriting with LLMs for Translating C to Safer Rust
by: Gao, Yifei, et al.
Published: (2025)

SWEnergy: An Empirical Study on Energy Efficiency in Agentic Issue Resolution Frameworks with SLMs
by: Tripathy, Arihant, et al.
Published: (2025)

David vs. Goliath: Can Small Models Win Big with Agentic AI in Hardware Design?
by: Shankar, Shashwat, et al.
Published: (2025)

On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset
by: Bhat, Vishvesh, et al.
Published: (2025)

An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software
by: Gogani-Khiabani, Sina, et al.
Published: (2025)

Expectations vs Reality -- A Secondary Study on AI Adoption in Software Testing
by: Karhu, Katja, et al.
Published: (2025)

Breaking the Illusion of Identity in LLM Tooling
by: Miller, Marek
Published: (2026)

PyGen: A Collaborative Human-AI Approach to Python Package Creation
by: Barua, Saikat, et al.
Published: (2024)

Agentic Business Process Management Systems
by: Dumas, Marlon, et al.
Published: (2026)

DeepCode: Open Agentic Coding
by: Li, Zongwei, et al.
Published: (2025)

Agentic Harness for Real-World Compilers
by: Zheng, Yingwei, 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)

Pragmos: A Process Agentic Modeling System
by: Hernández-Ávalos, Pedro-Aarón, et al.
Published: (2026)

Agentic Coding Needs Proactivity, Not Just Autonomy
by: Bui, Nghi D. Q., et al.
Published: (2026)

Agentic AI Software Engineers: Programming with Trust
by: Roychoudhury, Abhik, et al.
Published: (2025)

How Do LLMs Fail In Agentic Scenarios? A Qualitative Analysis of Success and Failure Scenarios of Various LLMs in Agentic Simulations
by: Roig, JV
Published: (2025)

Breaking Barriers in Software Testing: The Power of AI-Driven Automation
by: Naqvi, Saba, et al.
Published: (2025)

Breaking the Myth: Can Small Models Infer Postconditions Too?
by: Zhang, Gehao, et al.
Published: (2025)