Cover Image

Theory of Code Space: Do Code Agents Understand Software Architecture?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Sapunov, Grigory
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

Architecture Without Architects: How AI Coding Agents Shape Software Architecture
by: Konrad, Phongsakon Mark, et al.
Published: (2026)

ReDef: Do Code Language Models Truly Understand Code Changes for Just-in-Time Software Defect Prediction?
by: Nam, Doha, et al.
Published: (2025)

CodeSSM: Towards State Space Models for Code Understanding
by: Verma, Shweta, et al.
Published: (2025)

Do Code LLMs Understand Design Patterns?
by: Pan, Zhenyu, et al.
Published: (2025)

CIAO - Code In Architecture Out - Automated Software Architecture Documentation with Large Language Models
by: De Luca, Marco, et al.
Published: (2026)

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
by: Phan, Huy Nhat, et al.
Published: (2024)

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

Formal Architecture Descriptors as Navigation Primitives for AI Coding Agents
by: Jin, Ruoqi
Published: (2026)

CODESTRUCT: Code Agents over Structured Action Spaces
by: Kim, Myeongsoo, et al.
Published: (2026)

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

Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization
by: Peng, Huiyun, et al.
Published: (2026)

The Conversations Beneath the Code: Triadic Data for Long-Horizon Software Engineering Agents
by: Kim, Yelin
Published: (2026)

A Benchmark for Localizing Code and Non-Code Issues in Software Projects
by: Zhang, Zejun, et al.
Published: (2025)

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

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

AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development
by: Zhu, Yuecai, et al.
Published: (2026)

Beyond Isolated Tasks: A Framework for Evaluating Coding Agents on Sequential Software Evolution
by: Shastry, KN Ajay, et al.
Published: (2026)

Identifying Performance-Sensitive Configurations in Software Systems through Code Analysis with LLM Agents
by: Wang, Zehao, et al.
Published: (2024)

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

Generating Software Architecture Description from Source Code using Reverse Engineering and Large Language Model
by: Hatahet, Ahmad, et al.
Published: (2025)

Uncovering Code Insights: Leveraging GitHub Artifacts for Deeper Code Understanding
by: Nevo, Ziv, et al.
Published: (2025)

Code Review Agent Benchmark
by: Zhang, Yuntong, et al.
Published: (2026)

RepoReviewer: A Local-First Multi-Agent Architecture for Repository-Level Code Review
by: Zhang, Peng
Published: (2026)

SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents
by: Lin, Feng, et al.
Published: (2024)

Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents
by: Wang, Kaixin, et al.
Published: (2025)

CodeClash: Benchmarking Goal-Oriented Software Engineering
by: Yang, John, et al.
Published: (2025)

In-Context Code-Text Learning for Bimodal Software Engineering
by: Tang, Xunzhu, et al.
Published: (2024)

AI Code in the Wild: Measuring Security Risks and Ecosystem Shifts of AI-Generated Code in Modern Software
by: Wang, Bin, et al.
Published: (2025)

OmniCode: A Benchmark for Evaluating Software Engineering Agents
by: Sonwane, Atharv, et al.
Published: (2026)

CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs
by: Basha, Manaal, et al.
Published: (2025)

MASAI: Modular Architecture for Software-engineering AI Agents
by: Arora, Daman, et al.
Published: (2024)

Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests
by: Gong, Jingzhi, et al.
Published: (2026)

Code Researcher: Deep Research Agent for Large Systems Code and Commit History
by: Singh, Ramneet, et al.
Published: (2025)

The Code Barrier: What LLMs Actually Understand?
by: Nikiema, Serge Lionel, et al.
Published: (2025)

Understanding Defects in Generated Codes by Language Models
by: Esfahani, Ali Mohammadi, et al.
Published: (2024)

Do Machines and Humans Focus on Similar Code? Exploring Explainability of Large Language Models in Code Summarization
by: Li, Jiliang, et al.
Published: (2024)

Workflows vs Agents for Code Translation
by: Gray, Henry, et al.
Published: (2025)

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

Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study
by: Trivedi, Priyansh, et al.
Published: (2026)

ArchAgent: Scalable Legacy Software Architecture Recovery with LLMs
by: Pan, Rusheng, et al.
Published: (2026)