🤖 AI Summary
This study addresses the issue of application updates invalidating on-device cached experiences for GUI agents, thereby inducing silent errors. To mitigate this, we propose a version-key-based edge-cloud experience consistency maintenance mechanism. Specifically, we construct a collaborative repair protocol integrating cloud-side replay, edge-side verification, and incremental evidence transmission, while incorporating accessibility tree differencing to enable cross-version incremental experience patch generation. As the first framework of its kind, our approach restores experience recovery success rates to levels comparable with fresh data. Compared to baselines, it reduces communication bytes by 708×, cloud invocations by 47.3×, and energy consumption by 2.5×, significantly optimizing edge deployment efficiency.
📝 Abstract
A graphical user interface (GUI) agent that ships on a phone runs a small model and reuses experience: action paths recorded on earlier runs and cached from the cloud. When an app updates, part of this experience becomes silently wrong. On nine real app version pairs, an agent carrying experience recorded on the old version succeeds 10.1 points less often than one carrying none, and it does not notice the mismatch until 3 steps after acting on it. We propose REBASE, a protocol that keeps the device copy and the cloud copy of the experience coherent across updates. When a version changes, the cloud replays its copy on the new version and the device verifies each recorded step before executing it; when a step still fails, the device sends the cloud evidence in increasing size, starting from an accessibility-subtree diff, until the cloud re-derives an executable patch, keyed by version so that one repair serves the whole fleet. On two Jetson devices, REBASE restores the success rate of stale experience to that of fresh experience recorded on the new version within one episode, at 708x fewer bytes and 47.3x fewer cloud calls than uploading screenshots to the cloud, and 2.5x less device energy than running without experience.