Cover Image

Do Not Treat Code as Natural Language: Implications for Repository-Level Code Generation and Beyond

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Le-Anh, Minh, Nguyen, Huyen, Tran, Khanh An, Hai, Nam Le, Van, Linh Ngo, Bui, Nghi D. Q., Le, Bach
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

On the Impacts of Contexts on Repository-Level Code Generation
by: Hai, Nam Le, et al.
Published: (2024)

CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases
by: Hoang, Anh Nguyen, et al.
Published: (2025)

Documentation-Guided Agentic Codebase Migration from C to Rust
by: Le-Anh, Minh, et al.
Published: (2026)

Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals
by: Nghiem, Khanh, et al.
Published: (2024)

CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs
by: Manh, Dung Nguyen, et al.
Published: (2024)

RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion
by: Phan, Huy N., et al.
Published: (2024)

Detection of Technical Debt in Java Source Code
by: Hai, Nam Le, et al.
Published: (2024)

Functional Overlap Reranking for Neural Code Generation
by: To, Hung Quoc, et al.
Published: (2023)

DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies
by: Dau, Anh T. V., et al.
Published: (2023)

CodeFlow: Program Behavior Prediction with Dynamic Dependencies Learning
by: Le, Cuong Chi, et al.
Published: (2024)

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

VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning
by: Le, Cuong Chi, et al.
Published: (2024)

COBOLAssist: Analyzing and Fixing Compilation Errors for LLM-Powered COBOL Code Generation
by: Dau, Anh T. V., et al.
Published: (2026)

Beyond Localization: Recoverable Headroom and Residual Frontier in Repository-Level RAG-APR
by: Zhao, Pengtao, et al.
Published: (2026)

CodeTF: One-stop Transformer Library for State-of-the-art Code LLMs
by: Bui, Nghi D. Q., et al.
Published: (2023)

COBOL-Coder: Domain-Adapted Large Language Models for COBOL Code Generation and Translation
by: Dau, Anh T. V., et al.
Published: (2026)

Signature in Code Backdoor Detection, how far are we?
by: Le, Quoc Hung, et al.
Published: (2025)

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

EnseSmells: Deep ensemble and programming language models for automated code smells detection
by: Ho, Anh, et al.
Published: (2025)

Modeling Sampling Workflows for Code Repositories
by: Lefeuvre, Romain, et al.
Published: (2026)

Qualitative Coding Analysis through Open-Source Large Language Models: A User Study and Design Recommendations
by: Ngo, Tung T., et al.
Published: (2026)

iML: Executable, Problem-Grounded, and Broadly Exploratory Code-Driven AutoML
by: Le, Dat, et al.
Published: (2026)

Automated Code-centric Software Vulnerability Assessment: How Far Are We? An Empirical Study in C/C++
by: Nguyen, Anh The, et al.
Published: (2024)

When Retriever Meets Generator: A Joint Model for Code Comment Generation
by: Le, Tien P. T., et al.
Published: (2025)

Enhancing Program Repair with Specification Guidance and Intermediate Behavioral Signals
by: Le-Anh, Minh, et al.
Published: (2026)

Semantic Evolution over Populations for LLM-Guided Automated Program Repair
by: Le, Cuong Chi, et al.
Published: (2026)

The Effect of Code Obfuscation on Human Program Comprehension
by: Nguyen, Anh H. N., et al.
Published: (2026)

Larger Is Not Always Better: Leveraging Structured Code Diffs for Comment Inconsistency Detection
by: Nguyen, Phong, et al.
Published: (2025)

CodeLSI: Leveraging Foundation Models for Automated Code Generation with Low-Rank Optimization and Domain-Specific Instruction Tuning
by: Le, Huy, et al.
Published: (2025)

Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing
by: Le-Cong, Thanh, et al.
Published: (2024)

Perish or Flourish? A Holistic Evaluation of Large Language Models for Code Generation in Functional Programming
by: Lang, Nguyet-Anh H., et al.
Published: (2026)

Dopamin: Transformer-based Comment Classifiers through Domain Post-Training and Multi-level Layer Aggregation
by: Hai, Nam Le, et al.
Published: (2024)

Adversarial Attacks on Code Models with Discriminative Graph Patterns
by: Nguyen, Thanh-Dat, et al.
Published: (2023)

AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology
by: Nguyen, Minh Huynh, et al.
Published: (2024)

Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering
by: Alebachew, Yoseph Berhanu, et al.
Published: (2026)

SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs
by: Pham, Minh V. T., et al.
Published: (2025)

Good things come in three: Generating SO Post Titles with Pre-Trained Models, Self Improvement and Post Ranking
by: Le, Duc Anh, et al.
Published: (2024)

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

Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation
by: Wang, Chong, et al.
Published: (2024)

Measuring the Unmeasurable: Markov Chain Reliability for LLM Agents
by: Tran-Truong, Phat T., et al.
Published: (2026)