DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding
For developers of GUI agents, this work addresses the bottleneck of grounding instruction-relevant elements in cluttered high-resolution screenshots without requiring additional training.
DRS-GUI is a training-free dynamic region search framework that improves GUI grounding in MLLMs by mimicking human perceptual actions, achieving a 14% improvement on ScreenSpot-Pro for models like Qwen2.5-VL-7B and UGround-V1-7B.
GUI agents powered by Multimodal Large Language Models (MLLMs) have demonstrated impressive capability in understanding and executing user instructions. However, accurately grounding instruction-relevant elements from high-resolution screenshots cluttered with irrelevant UI components remains challenging for existing approaches. Inspired by how humans dynamically adjust their perceptual scope to locate task-related regions on complex screens, we propose DRS-GUI, a training-free dynamic region search framework for GUI grounding that can be seamlessly integrated into existing MLLMs. DRS-GUI introduces a lightweight UI Perceptor that performs three human-like perceptual actions (Focus, Shift, and Scatter) to progressively explore the interface and generate region proposals. To dynamically schedule these actions, we further design an Action Planner based on Monte Carlo Tree Search (MCTS). A region quality reward is employed to evaluate and select the highly instruction-relevant region, efficiently pruning redundant UI elements. Experiments demonstrate that DRS-GUI yields a 14\% improvement on ScreenSpot-Pro for general and GUI-specific MLLMs (Qwen2.5-VL-7B and UGround-V1-7B), significantly enhancing grounding performance and generalization.