SOURCE-LINKED INTELLIGENCE

CURA: Certified Runtime Alarms for Computer-Use Agents

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

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 GUI executor, reaches a mean task score of 82.9, above the 72.4 human reference, yet 64 of its 71 failures (90%) end with a success claim, 61 acknowledging no blocker, and the explicit failure affordance is never used in roughly 9,100 calls. We introduce CURA (Certified Runtime Alarms for Computer-Use Agents), an external monitor that reads only harness-visible teleme

Read original source ↗ Open in workspace

recordType

paper

region

Global