AI RESEARCH
Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
arXiv CS.AI
•
ArXi:2603.11214v1 Announce Type: new We evaluate the autonomous cyber-attack capabilities of frontier AI models on two purpose-built cyber ranges-a 32-step corporate network attack and a 7-step industrial control system attack-that require chaining heterogeneous capabilities across extended action sequences. By comparing seven models released over an eighteen-month period (August 2024 to February 2026) at varying inference-time compute budgets, we observe two capability trends.