Imagen de Portada

An Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Saju, Md Hasan, Muhtadi, Maher, Azim, Akramul
Formato:	Preprint
Publicado:	2026
Materias:	Software Engineering Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements
por: Abtahi, Seyed Moein, et al.
Publicado: (2025)

Toward Autonomous SOC Operations: End-to-End LLM Framework for Threat Detection, Query Generation, and Resolution in Security Operations
por: Saju, Md Hasan, et al.
Publicado: (2026)

WALL: A Web Application for Automated Quality Assurance using Large Language Models
por: Abtahi, Seyed Moein, et al.
Publicado: (2025)

Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG
por: Du, Xueying, et al.
Publicado: (2024)

From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection
por: Li, Youpeng, et al.
Publicado: (2026)

Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents
por: Widyasari, Ratnadira, et al.
Publicado: (2025)

The Code Whisperer: LLM and Graph-Based AI for Smell and Vulnerability Resolution
por: Baqar, Mohammad, et al.
Publicado: (2026)

An Empirical Study of the Imbalance Issue in Software Vulnerability Detection
por: Guo, Yuejun, et al.
Publicado: (2026)

LLMs in Web Development: Evaluating LLM-Generated PHP Code Unveiling Vulnerabilities and Limitations
por: Tóth, Rebeka, et al.
Publicado: (2024)

Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report
por: Khan, Ayman Asad, et al.
Publicado: (2024)

The Tyranny of Possibilities in the Design of Task-Oriented LLM Systems: A Scoping Survey
por: Dhamani, Dhruv, et al.
Publicado: (2023)

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

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

MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution
por: Wu, Zihan, et al.
Publicado: (2026)

LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward
por: Islam, Nafis Tanveer, et al.
Publicado: (2024)

Machine Learning Techniques for Python Source Code Vulnerability Detection
por: Farasat, Talaya, et al.
Publicado: (2024)

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

MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems
por: Jia, Jin, et al.
Publicado: (2026)

SynRAG: A Large Language Model Framework for Executable Query Generation in Heterogeneous SIEM System
por: Saju, Md Hasan, et al.
Publicado: (2025)

Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents Approach
por: Ashiga, Mari, et al.
Publicado: (2025)

An Empirical Study of Vulnerabilities in Python Packages and Their Detection
por: Quan, Haowei, et al.
Publicado: (2025)

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

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

Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis
por: Akli, Amal, et al.
Publicado: (2026)

Vendor-Aware Industrial Agents: RAG-Enhanced LLMs for Secure On-Premise PLC Code Generation
por: Kersting, Joschka, et al.
Publicado: (2025)

CGP-Tuning: Structure-Aware Soft Prompt Tuning for Code Vulnerability Detection
por: Feng, Ruijun, et al.
Publicado: (2025)

AutoEmpirical: LLM-Based Automated Research for Empirical Software Fault Analysis
por: Yu, Jiongchi, et al.
Publicado: (2025)

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

Designing Empirical Studies on LLM-Based Code Generation: Towards a Reference Framework
por: Nascimento, Nathalia, et al.
Publicado: (2025)

ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents
por: He, Jiawei, et al.
Publicado: (2026)

An Empirical Study of Vulnerability Detection using Federated Learning
por: Zhou, Peiheng, et al.
Publicado: (2024)

From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification
por: Erfan, Md, et al.
Publicado: (2026)

Specification and Detection of LLM Code Smells
por: Mahmoudi, Brahim, et al.
Publicado: (2025)

Open the Oyster: Empirical Evaluation and Improvement of Code Reasoning Confidence in LLMs
por: Wang, Shufan, et al.
Publicado: (2025)

Towards AI Evaluation in Domain-Specific RAG Systems: The AgriHubi Case Study
por: Hasan, Md. Toufique, et al.
Publicado: (2026)

Studying Vulnerable Code Entities in R
por: Zhao, Zixiao, et al.
Publicado: (2024)

An Empirical Evaluation of Locally Deployed LLMs for Bug Detection in Python Code
por: Vulićević, Jelena Ilić
Publicado: (2026)

SpecMap: Hierarchical LLM Agent for Datasheet-to-Code Traceability Link Recovery in Systems Engineering
por: Nipane, Vedant, et al.
Publicado: (2026)

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach
por: Sepidband, Melika, et al.
Publicado: (2025)

EvalSVA: Multi-Agent Evaluators for Next-Gen Software Vulnerability Assessment
por: Wen, Xin-Cheng, et al.
Publicado: (2024)