Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction
FuzzingBrain V2 is a multi-agent system designed to enhance automated vulnerability discovery and reproduction. It addresses challenges such as high false positive rates and suboptimal vulnerability localization in existing LLM approaches. The system has demonstrated a 90% detection rate and discovered multiple zero-day vulnerabilities in real-world applications.
- ▪Nearly 50,000 CVEs were reported in 2025, highlighting the critical need for improved vulnerability detection.
- ▪FuzzingBrain V2 achieved a 90% detection rate on the AIxCC 2025 Final Competition dataset.
- ▪The system discovered 29 zero-day vulnerabilities across 12 open-source projects, all confirmed and fixed by maintainers.
2 outlets in our directory ran this story, first to last over 14 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,611 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2605.21779 |
| Publication time | Wed, 27 May 2026 17:42:24 +0000 |
| Retrieval time | 2026-05-27T17:48:02.496Z |
| Last seen | 2026-05-27T17:48:02.496Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | -geC0RFX4E91 · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Cryptography and Security arXiv:2605.21779 (cs) [Submitted on 20 May 2026] Title:FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction Authors:Ze Sheng, Zhicheng Chen, Qingxiao Xu, Kewen Zhu, Jeff Huang View a PDF of the paper titled FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction, by Ze Sheng and 4 other authors View PDF HTML (experimental) 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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
