AI RESEARCH
Rethinking Token Pruning for Historical Screenshots in GUI Visual Agents: Semantic, Spatial, and Temporal Perspectives
arXiv CS.CV
•
ArXi:2603.26041v1 Announce Type: new In recent years, GUI visual agents built upon Multimodal Large Language Models (MLLMs) have nstrated strong potential in navigation tasks. However, high-resolution GUI screenshots produce a large number of visual tokens, making the direct preservation of complete historical information computationally expensive. In this paper, we conduct an empirical study on token pruning for historical screenshots in GUI scenarios and distill three practical insights that are crucial for designing effective pruning strategies.