# GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs

arXiv: https://arxiv.org/abs/2608.03270 · HTML: https://mlsanity.com/paper/2608.03270/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents](https://mlsanity.com/paper/2410.05243/) (2024)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use](https://mlsanity.com/paper/2504.07981/) (2025)
- [ShowUI: One Vision-Language-Action Model for GUI Visual Agent](https://mlsanity.com/paper/2411.17465/) (2024)
- [OmniParser for Pure Vision Based GUI Agent](https://mlsanity.com/paper/2408.00203/) (2024)
- [GUI Agents with Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2411.04890/) (2024)
- [GTA1: GUI Test-time Scaling Agent](https://mlsanity.com/paper/2507.05791/) (2025)
- [GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents](https://mlsanity.com/paper/2506.03143/) (2025)
- [UI-Venus Technical Report: Building High-performance UI Agents with RFT](https://mlsanity.com/paper/2508.10833/) (2025)
- [MAI-UI Technical Report: Real-World Centric Foundation GUI Agents](https://mlsanity.com/paper/2512.22047/) (2025)
- [MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents](https://mlsanity.com/paper/2507.19478/) (2025)
- [UI-Venus-1.5 Technical Report](https://mlsanity.com/paper/2602.09082/) (2026)
- [MVP: Multiple View Prediction Improves GUI Grounding](https://mlsanity.com/paper/2512.08529/) (2025)
- [Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding](https://mlsanity.com/paper/2512.05941/) (2025)
- [AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement](https://mlsanity.com/paper/2603.17441/) (2026)
- [DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding](https://mlsanity.com/paper/2605.15542/) (2026)

## Abstract (arXiv)

GUI grounding maps natural-language instructions to click locations and is essential for reliable GUI agents. The task remains difficult on high-resolution, densely populated interfaces because a vision-language model (VLM) may recognize a requested control without locating it precisely enough for interaction. Most existing methods provide various forms of localization assistance, but still rely on a direct click prediction, allowing visual ambiguity or an inaccurate initial estimate to propagate to the final result. In this paper, we introduce GUI-Lens, a coarse-to-fine grounding framework that allows a general-purpose VLM to determine the target through active visual observations. Specifically, GUI-Lens extracts OCR text and detected UI components from the screenshot and presents their positions as coordinate references. Using the instruction, the current view, and these references, the VLM selects the region and scale of the next view, which is cropped and enlarged to provide finer visual details. This process continues over successively focused views until the target is determined. Proposed crops and clicks are checked against the instruction throughout the process, and the final local position is mapped back to the original screen coordinates. Experiments on four GUI grounding benchmarks and three general-purpose VLM backends show that GUI-Lens improves overall grounding accuracy by up to 24.9 percentage points and achieves state-of-the-art performance with GPT-5.5.