SOURCE-LINKED INTELLIGENCE

TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

GUI agents accumulate high-resolution screenshots as the trajectory unfolds, increasing inference latency and memory usage. Training-free visual token pruning can reduce this cost, but cache reuse introduces a fundamental constraint. Once tokens are discarded, the corresponding visual evidence cannot be recovered without re-encoding. Pruning therefore becomes an \textit{irreversible admission decision} that must remain useful for unknown future targets while preserving coverage of operable regions under tight budgets. To address these challenges, we propose \textbf{\method{}}, a training-free

Read original source ↗ Open in workspace

recordType

paper

region

Global