CURA: Certified Runtime Alarms for Computer-Use Agents
This work introduces CURA (Certified Runtime Alarms for Computer-Use Agents), an external monitor that reads only harness-visible telemetry, with no model internals, extra LLM calls, or prompt changes, and turns the running trajectory into a sequential test with certified false-alarm control.
Divake Kumar, Sina Tayebati, Devashri Naik et al.
· 0 citations