Microsoft’s multi-agent security system found 16 Patch Tuesday bugs

More than 100 specialized agents across frontier and custom models topped CyberGym and were used before Patch Tuesday

Our new multi-model agentic security system brings together more than 100 specialized agents across frontier and custom models to find exploitable bugs, delivering top performance on the CyberGym benchmark. We used it ahead of Patch Tuesda
Ranked #6 on backlist 2026-05-13 (13 May 2026 UTC) · by (Satya Nadella) ·

How it ranks: Backlist reads my Twitter/X timeline, scores every tweet for substance with an LLM rubric (not engagement), and publishes the daily top picks with a one-line takeaway. Curated by Surya Dantuluri.