Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction

Researchers have developed FuzzingBrain V2, a multi-agent large language model system that automatically discovers and reproduces software vulnerabilities. The system achieved a 90% detection rate on a competition dataset and found 29 zero-day vulnerabilities across 12 open-source projects, all confirmed and fixed by maintainers. The approach addresses high false positive rates and complex cross-function vulnerability reasoning by integrating fuzzer-reproducible verification and a novel control-flow-based abstraction for precise localization.

Computer Science Cryptography and Security Submitted on 20 May 2026 Title:FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction View PDF /pdf/2605.21779 HTML experimental https://arxiv.org/html/2605.21779v1 Abstract:Software vulnerabilities pose critical security threats, with nearly 50,000 CVEs reported in 2025. While Large Language Models LLMs show promise for automated vulnerability detection, three key challenges remain. First, LLM-generated vulnerability reports suffer from high false positive rates and lack reproducible verification. Second, existing LLM-based approaches use suboptimal granularities for vulnerability localization: function-level analysis overlooks bugs when context becomes extensive, while line-level analysis lacks sufficient context. Third, existing approaches have difficulty reasoning about vulnerabilities with complex cross-function dependencies and triggering conditions. We present FuzzingBrain V2, a multi-agent system that addresses these gaps through four key contributions: 1 fully automated vulnerability analysis built on Google's OSS-Fuzz, ensuring all reported vulnerabilities are fuzzer-reproducible; 2 Suspicious Point, a novel control-flow-based abstraction for precise vulnerability localization at the optimal granularity; 3 logic-driven hierarchical function analysis with dual-layer fuzzing enhancing function coverage under resource constraints; 4 MCP-based static and dynamic analysis tools with context engineering enhancing complex vulnerability reasoning. On the AIxCC 2025 Final Competition C/C++ dataset, FuzzingBrain V2 achieved 90% detection rate 36 of 40 vulnerabilities . In real-world deployment, FuzzingBrain V2 discovered 29 zero-day vulnerabilities across 12 open-source projects, all confirmed and fixed by maintainers, with 2 assigned CVE IDs. References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .