# FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction

arXiv: https://arxiv.org/abs/2605.21779 · HTML: https://mlsanity.com/paper/2605.21779/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 13 of 13)

- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019)
- [Do Users Write More Insecure Code with AI Assistants?](https://mlsanity.com/paper/2211.03622/) (2022)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities](https://mlsanity.com/paper/2405.17238/) (2024)
- [Fuzz4All: Universal Fuzzing with Large Language Models](https://mlsanity.com/paper/2308.04748/) (2023)
- [Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG](https://mlsanity.com/paper/2406.11147/) (2024)
- [LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning](https://mlsanity.com/paper/2401.16185/) (2024)
- [VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection](https://mlsanity.com/paper/2205.12424/) (2022)
- [LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights](https://mlsanity.com/paper/2502.07049/) (2025)
- [Large Language Model for Vulnerability Detection and Repair: Literature Review and the Road Ahead](https://mlsanity.com/paper/2404.02525/) (2024)
- [WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models](https://mlsanity.com/paper/2310.15991/) (2023)
- [Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities](https://mlsanity.com/paper/2405.12750/) (2024)

## Built on by (most cited first, 3 of 3)

- [Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities](https://mlsanity.com/paper/2606.26933/) (2026)
- [FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs](https://mlsanity.com/paper/2608.25158/) (2026)
- [QuSema: Detecting Silent Bugs in Quantum Libraries via Quantum-knowledge-enhanced Agents](https://mlsanity.com/paper/2610.10258/) (2026)

## Abstract (arXiv)

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.