Microsoft launches multi-model AI security system with over 100 agents to find vulnerabilities
Original title:Our new multi-model agentic security system brings together more than 100 specialized agents across ...
AI summary
Microsoft launched a new multi-model agentic security system that integrates more than 100 specialized agents built on frontier and custom models to find exploitable security vulnerabilities. The system achieved top performance on the CyberGym benchmark. Ahead of the most recent Patch Tuesday, it helped find and fix 16 vulnerabilities. Microsoft announced that customers can now apply to join a private preview of the system.
Key Takeaways
- Microsoft launched a new multi-model agentic security system that integrates more than 100…
- The system achieved top performance on the CyberGym benchmark.
- Ahead of the most recent Patch Tuesday,it helped find and fix 16 vulnerabilities.
- Microsoft announced that customers can now apply to join a private preview of the system.
Quick Facts
- Published
- Updated
- Category
- Products & Apps
- AI score
- 68
微软把多模型代理系统用到安全漏洞挖掘上,100多个专业代理协作,在CyberGym基准拿了第一,做安全的朋友值得看看实际效果。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Microsoft launches multi-model AI security system with over 100 agents to find vulnerabilities. May 13, 2026. https://new.nat6.net/en/news/cmp3b31ul04kksl1q1dhdy9b9/