Cover Image

Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Majgaonkar, Oorja, Fei, Zhiwei, Li, Xiang, Sarro, Federica, Ye, He
Format:	Preprint
Published:	2025
Subjects:	Software Engineering Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Compression of Language Models for Code: An Empirical Study on CodeBERT
by: d'Aloisio, Giordano, et al.
Published: (2024)

Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents
by: Li, Xiang, et al.
Published: (2026)

Generative AI for Testing of Autonomous Driving Systems: A Survey
by: Song, Qunying, et al.
Published: (2025)

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
by: Gong, Jingzhi, et al.
Published: (2026)

An Empirical Study of Knowledge Distillation for Code Understanding Tasks
by: Wang, Ruiqi, et al.
Published: (2025)

How Do Generative Models Draw a Software Engineer? A Case Study on Stable Diffusion Bias
by: Fadahunsi, Tosin, et al.
Published: (2025)

An Empirical Study of Proactive Coding Assistants in Real-World Software Development
by: Li, Lehui, et al.
Published: (2026)

How Do Agents Perform Code Optimization? An Empirical Study
by: Peng, Huiyun, et al.
Published: (2025)

An Empirical Study on Capability of Large Language Models in Understanding Code Semantics
by: Nguyen, Thu-Trang, et al.
Published: (2024)

When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions
by: Larbi, Maya, et al.
Published: (2025)

On The Effectiveness of One-Class Support Vector Machine in Different Defect Prediction Scenarios
by: Moussa, Rebecca, et al.
Published: (2022)

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

Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study
by: Ceka, Ira, et al.
Published: (2025)

Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories
by: Bouzenia, Islem, et al.
Published: (2025)

SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Models
by: d'Aloisio, Giordano, et al.
Published: (2025)

An Empirical Study on Failures in Automated Issue Solving
by: Liu, Simiao, et al.
Published: (2025)

Beyond Autoregression: An Empirical Study of Diffusion Large Language Models for Code Generation
by: Li, Chengze, et al.
Published: (2025)

Theory of Code Space: Do Code Agents Understand Software Architecture?
by: Sapunov, Grigory
Published: (2026)

Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation
by: Vartziotis, Tina, et al.
Published: (2024)

An Empirical Study of Agent Developer Practices in AI Agent Frameworks
by: Wang, Yanlin, et al.
Published: (2025)

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

HerAgent: Rethinking the Automated Environment Deployment via Hierarchical Test Pyramid
by: Li, Xiang, et al.
Published: (2026)

Bugs in Large Language Models Generated Code: An Empirical Study
by: Tambon, Florian, et al.
Published: (2024)

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

An Empirical Study on LLM-based Agents for Automated Bug Fixing
by: Meng, Xiangxin, et al.
Published: (2024)

Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation
by: Lyu, Zongyi, et al.
Published: (2025)

More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents
by: Gao, Pengfei, et al.
Published: (2025)

Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?
by: Pan, Zhenyu, et al.
Published: (2024)

AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents
by: Vangala, Bhanu Prakash, et al.
Published: (2025)

An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation
by: Gandhi, Shubham, et al.
Published: (2025)

Philosophical Dispositions as Behavioral Constraints for AI-Assisted Code Review: An Empirical Study
by: Bansal, Kaushal
Published: (2026)

Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Study
by: Dong, Zeming, et al.
Published: (2023)

FastCode: Fast and Cost-Efficient Code Understanding and Reasoning
by: Li, Zhonghang, et al.
Published: (2026)

Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation
by: Zhang, Lingzhe, et al.
Published: (2026)

An Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent Systems
by: Saju, Md Hasan, et al.
Published: (2026)

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents
by: Fei, Xiang, et al.
Published: (2025)

An Empirical Study on Self-correcting Large Language Models for Data Science Code Generation
by: Quoc, Thai Tang, et al.
Published: (2024)

An Empirical Study of OpenAI API Discussions on Stack Overflow
by: Chen, Xiang, et al.
Published: (2025)

Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation
by: Jia, Haoxiang, et al.
Published: (2025)

Empirical Studies of Parameter Efficient Methods for Large Language Models of Code and Knowledge Transfer to R
by: Esmaeili, Amirreza, et al.
Published: (2024)