Cover Image

Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mehtiyev, Tural, Assunção, Wesley
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

Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories
by: Majgaonkar, Oorja, et al.
Published: (2025)

Test Code Review in the Era of GitHub Actions: A Replication Study
by: Sun, Hui, et al.
Published: (2026)

Is LLM-Generated Code More Maintainable \& Reliable than Human-Written Code?
by: Molison, Alfred Santa, et al.
Published: (2025)

Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints
by: Li, Kefan, et al.
Published: (2026)

Code Quality Analysis of Translations from C to Rust
by: Tadesse, Biruk, et al.
Published: (2026)

SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution
by: Raghavendra, Mohit, et al.
Published: (2026)

Assessing the Bug-Proneness of Refactored Code: A Longitudinal Multi-Project Study
by: Ferreira, Isabella, et al.
Published: (2025)

Where are the Hidden Gems? Applying Transformer Models for Design Discussion Detection
by: Arkoh, Lawrence, et al.
Published: (2026)

Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation
by: Rabbi, Fazle, et al.
Published: (2026)

ABTest: Behavior-Driven Testing for AI Coding Agents
by: Dai, Wuyang, et al.
Published: (2026)

Model-based Maintenance and Evolution with GenAI: A Look into the Future
by: Marchezan, Luciano, et al.
Published: (2024)

Contemporary Software Modernization: Perspectives and Challenges to Deal with Legacy Systems
by: Assunção, Wesley K. G., et al.
Published: (2024)

Refactoring $\neq$ Bug-Inducing: Improving Defect Prediction with Code Change Tactics Analysis
by: Niu, Feifei, et al.
Published: (2025)

Brevity is the Soul of Wit: Condensing Code Changes to Improve Commit Message Generation
by: Kuang, Hongyu, et al.
Published: (2025)

Feature-oriented Test Case Selection and Prioritization During the Evolution of Highly-Configurable Systems
by: Mendonça, Willian D. F., et al.
Published: (2024)

A Large-Scale Study on Developer Engagement and Expertise in Configurable Software System Projects
by: Milano, Karolina M., et al.
Published: (2025)

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

SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle
by: Guan, Hao, et al.
Published: (2026)

Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation
by: Moumoula, Micheline Bénédicte, et al.
Published: (2025)

Developer Experience with AI Coding Agents: HTTP Behavioral Signatures in Documentation Portals
by: Borysenko, Oleksii
Published: (2026)

Accountability in Code Review: The Role of Intrinsic Drivers and the Impact of LLMs
by: Alami, Adam, et al.
Published: (2025)

From PREVENTion to REACTion: Enhancing Failure Resolution in Naval Systems
by: Rossi, Maria Teresa, et al.
Published: (2025)

On the Illusion of Success: An Empirical Study of Build Reruns and Silent Failures in Industrial CI
by: Aïdasso, Henri, et al.
Published: (2025)

An Empirical Study on Challenges of Event Management in Microservice Architectures
by: Laigner, Rodrigo, et al.
Published: (2024)

CodeAgent: Autonomous Communicative Agents for Code Review
by: Tang, Xunzhu, et al.
Published: (2024)

RefModel: Detecting Refactorings using Foundation Models
by: Simões, Pedro, et al.
Published: (2025)

Making OpenAPI Documentation Agent-Ready: Detecting Documentation and REST Smells with a Multi-Agent LLM System
by: Lima, Rayfran Rocha, et al.
Published: (2026)

What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants
by: Hasan, Alif Al, et al.
Published: (2026)

Relating Complexity, Explicitness, Effectiveness of Refactorings and Non-Functional Requirements: A Replication Study
by: Soares, Vinícius, et al.
Published: (2025)

RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
by: Guo, Chengquan, et al.
Published: (2025)

Beyond Code Generation: Assessing Code LLM Maturity with Postconditions
by: He, Fusen, et al.
Published: (2024)

Articulate but Wrong: Self-Review Failures in LLM-Based Code Modernization
by: Reddy, Gokul Chandra Purnachandra, et al.
Published: (2026)

Beyond Bug Fixes: An Empirical Investigation of Post-Merge Code Quality Issues in Agent-Generated Pull Requests
by: Cynthia, Shamse Tasnim, et al.
Published: (2026)

Compressing Code Context for LLM-based Issue Resolution
by: Jia, Haoxiang, et al.
Published: (2026)

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
by: Chen, Guoxin, et al.
Published: (2026)

Assessing, Exploiting, and Mitigating Syntactic Robustness Failures in LLM-Based Code Generation
by: Sarker, Laboni, et al.
Published: (2024)

Improving the Learning of Code Review Successive Tasks with Cross-Task Knowledge Distillation
by: Sghaier, Oussama Ben, et al.
Published: (2024)

CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
by: Zhang, Kechi, et al.
Published: (2024)

AgentFM: Role-Aware Failure Management for Distributed Databases with LLM-Driven Multi-Agents
by: Zhang, Lingzhe, et al.
Published: (2025)

Insights on Microservice Architecture Through the Eyes of Industry Practitioners
by: Nogueira, Vinicius L., et al.
Published: (2024)