arXiv CS AI
techLean Right
CURA: Certified Runtime Alarms for Computer-Use Agentstranslating…
arXiv:2608.27808v1 Announce Type: new
Abstract: Self-report is the cheapest oversight channel a deployer has, and on capable computer-use agents (CUAs) it fails precisely where oversight matters. On 361 OSWorld tasks our pipeline, a read-only feasibility gate, a planner, and a…
Keywords#Computer-Use Agents#Alarms#Certified#Certified Runtime#Certified Runtime Alarms