# AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement

arXiv: https://arxiv.org/abs/2603.17441 · HTML: https://mlsanity.com/paper/2603.17441/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 18 of its 21 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 18 of 18)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024)
- [Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents](https://mlsanity.com/paper/2410.05243/) (2024)
- [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use](https://mlsanity.com/paper/2504.07981/) (2025)
- [Mobile-Agent-v3: Fundamental Agents for GUI Automation](https://mlsanity.com/paper/2508.15144/) (2025)
- [OpenCUA: Open Foundations for Computer-Use Agents](https://mlsanity.com/paper/2508.09123/) (2025)
- [OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web](https://mlsanity.com/paper/2402.17553/) (2024)
- [InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners](https://mlsanity.com/paper/2504.14239/) (2025)
- [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)
- [MAI-UI Technical Report: Real-World Centric Foundation GUI Agents](https://mlsanity.com/paper/2512.22047/) (2025)
- [GUI-G2: Gaussian Reward Modeling for GUI Grounding](https://mlsanity.com/paper/2507.15846/) (2025)
- [R-VLM: Region-Aware Vision Language Model for Precise GUI Grounding](https://mlsanity.com/paper/2507.05673/) (2025)

## Built on by (most cited first, 6 of 6)

- [Zoom Consistency: A Free Confidence Signal in Multi-Step Visual Grounding Pipelines](https://mlsanity.com/paper/2604.15376/) (2026)
- [GUI-C2: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning](https://mlsanity.com/paper/2605.30884/) (2026)
- [One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding](https://mlsanity.com/paper/2606.30084/) (2026)
- [Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability](https://mlsanity.com/paper/2605.07110/) (2026)
- [GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs](https://mlsanity.com/paper/2608.03270/) (2026)
- [MHVF: Training-Free GUI Grounding via Verification-Guided Multi-Hypothesis Search](https://mlsanity.com/paper/2610.17792/) (2026)

## Abstract (arXiv)

GUI grounding is a critical capability for vision-language models (VLMs) that enables automated interaction with graphical user interfaces by locating target elements from natural language instructions. However, grounding on GUI screenshots remains challenging due to high-resolution images, small UI elements, and ambiguous user instructions. In this work, we propose AdaZoom-GUI, an adaptive zoom-based GUI grounding framework that improves both localization accuracy and instruction understanding. Our approach introduces an instruction refinement module that rewrites natural language commands into explicit and detailed descriptions, allowing the grounding model to focus on precise element localization. In addition, we design a conditional zoom-in strategy that selectively performs a second-stage inference on predicted small elements, improving localization accuracy while avoiding unnecessary computation and context loss on simpler cases. To support this framework, we construct a high-quality GUI grounding dataset and train the grounding model using Group Relative Policy Optimization (GRPO), enabling the model to predict both click coordinates and element bounding boxes. Experiments on public benchmarks demonstrate that our method achieves state-of-the-art performance among models with comparable or even larger parameter sizes, highlighting its effectiveness for high-resolution GUI understanding and practical GUI agent deployment.