Architectural choices can triple multi‑agent attack success while keeping performance steady
A new ICML 2026 study shows that the way agents are wired—roles, communication topology, and shared memory—can change misuse risk by up to 3.8×, even when task accuracy stays the same. No architecture is universally safe, so developers must empirically test security beyond single‑agent metrics. The authors release the Orbit framework and code for further work.