This paper builds a big, reusable library of computer skills so an AI can use Windows apps more like a careful human, not a clumsy robot.
SPARK is a new way to train AI agents that saves compute by exploring more only at the most important moments.
Computer-using agents kept forgetting important visual details over long tasks and could not reliably find up-to-date, step-by-step help for unfamiliar apps.
Robots usually learn by copying many demonstrations, which is expensive and makes them brittle when things change.