SOURCE-LINKED INTELLIGENCE

Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

GUI agents increasingly operate across websites, mobile apps, and desktop environments, yet the field still reports progress primarily through task success. We argue that practical deployment depends equally on efficiency: how much context, computation, action budget, and runtime overhead an agent consumes while succeeding. This survey studies efficient GUI agents through an end-to-end systems lens that preserves the current technical axes of observation efficiency, context and memory efficiency, action efficiency, and planner-side/system efficiency. For each subsection, we expand the seed lit

Read original source ↗ Open in workspace

recordType

paper

region

Global