Image de couverture de livre

A Dual-Loop Agent Framework for Automated Vulnerability Reproduction

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Bin, Zhao, Yanjie, Chen, Zhenpeng, Xu, Guoai, Wang, Haoyu
Format:	Preprint
Publié:	2026
Sujets:	Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?
par: Liu, Bin, et autres
Publié: (2025)

Agent-Based Software Artifact Evaluation
par: Wu, Zhaonan, et autres
Publié: (2026)

Same App, Different Behaviors: Uncovering Device-specific Behaviors in Android Apps
par: Dong, Zikan, et autres
Publié: (2024)

CommitShield: Tracking Vulnerability Introduction and Fix in Version Control Systems
par: Wu, Zhaonan, et autres
Publié: (2025)

Understanding Large Language Model Supply Chain: Structure, Domain, and Vulnerabilities
par: Hu, Yanzhe, et autres
Publié: (2025)

LaQual: A Novel Framework for Automated Evaluation of LLM App Quality
par: Wang, Yan, et autres
Publié: (2025)

FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction
par: Sheng, Ze, et autres
Publié: (2026)

Bridging Design and Development with Automated Declarative UI Code Generation
par: Zhou, Ting, et autres
Publié: (2024)

Voices from the Frontier: A Comprehensive Analysis of the OpenAI Developer Forum
par: Hou, Xinyi, et autres
Publié: (2024)

Decoding Secret Memorization in Code LLMs Through Token-Level Characterization
par: Nie, Yuqing, et autres
Publié: (2024)

VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution
par: Zhang, Mingming, et autres
Publié: (2026)

Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem
par: Hou, Xinyi, et autres
Publié: (2026)

WaDec: Decompiling WebAssembly Using Large Language Model
par: She, Xinyu, et autres
Publié: (2024)

Towards Trustworthy LLMs for Code: A Data-Centric Synergistic Auditing Framework
par: Wang, Chong, et autres
Publié: (2024)

LLM App Store Analysis: A Vision and Roadmap
par: Zhao, Yanjie, et autres
Publié: (2024)

GPTZoo: A Large-scale Dataset of GPTs for the Research Community
par: Hou, Xinyi, et autres
Publié: (2024)

Large Language Model Supply Chain: A Research Agenda
par: Wang, Shenao, et autres
Publié: (2024)

Wired for Reuse: Automating Context-Aware Code Adaptation in IDEs via LLM-Based Agent
par: Wang, Taiming, et autres
Publié: (2025)

Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks
par: Ke, Qiang, et autres
Publié: (2026)

VFArchē: A Dual-Mode Framework for Locating Vulnerable Functions in Open-Source Software
par: Zhang, Lyuye, et autres
Publié: (2025)

APIGen: Generative API Method Recommendation
par: Chen, Yujia, et autres
Publié: (2024)

LLM Applications: Current Paradigms and the Next Frontier
par: Hou, Xinyi, et autres
Publié: (2025)

Towards Reliable Vector Database Management Systems: A Software Testing Roadmap for 2030
par: Wang, Shenao, et autres
Publié: (2025)

A Prompt-Based Framework for Loop Vulnerability Detection Using Local LLMs
par: Adeseye, Adeyemi, et autres
Publié: (2026)

Toward Understanding Bugs in Vector Database Management Systems
par: Xie, Yinglin, et autres
Publié: (2025)

SoK: Automated Vulnerability Repair: Methods, Tools, and Assessments
par: Hu, Yiwei, et autres
Publié: (2025)

A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and Reflection
par: Chen, Siyi, et autres
Publié: (2026)

Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation
par: Li, Haoyu, et autres
Publié: (2026)

Patch Validation in Automated Vulnerability Repair
par: Yu, Zheng, et autres
Publié: (2026)

CommitSuite: A Comprehensive Benchmark for Commit Classification and Message Generation
par: Wan, Zirui, et autres
Publié: (2026)

FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents
par: Nitin, Vikram, et autres
Publié: (2025)

Can Agents Fix Agent Issues?
par: Rahardja, Alfin Wijaya, et autres
Publié: (2025)

Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps
par: Wang, Dingbang, et autres
Publié: (2024)

CodeMorph: Mitigating Data Leakage in Large Language Model Assessment
par: Rao, Hongzhou, et autres
Publié: (2025)

Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classification
par: Wu, Zehao, et autres
Publié: (2025)

Does the Vulnerability Threaten Our Projects? Automated Vulnerable API Detection for Third-Party Libraries
par: Zhang, Fangyuan, et autres
Publié: (2024)

Issue-Oriented Agent-Based Framework for Automated Review Comment Generation
par: Li, Shuochuan, et autres
Publié: (2025)

There are More Fish in the Sea: Automated Vulnerability Repair via Binary Templates
par: Lin, Bo, et autres
Publié: (2024)

Agent That Debugs: Dynamic State-Guided Vulnerability Repair
par: Liu, Zhengyao, et autres
Publié: (2025)

Large Language Model-Based Agents for Software Engineering: A Survey
par: Liu, Junwei, et autres
Publié: (2024)