GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding

• URL: http://arxiv.org/abs/2507.15846v3
• Date: Mon, 28 Jul 2025 16:54:13 GMT
• Title: GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding
• Authors: Fei Tang, Zhangxuan Gu, Zhengxi Lu, Xuyang Liu, Shuheng Shen, Changhua Meng, Wen Wang, Wenqi Zhang, Yongliang Shen, Weiming Lu, Jun Xiao, Yueting Zhuang,
• Abstract summary: Graphical User Interface (GUI) grounding maps natural language instructions to precise interface locations for autonomous interaction.<n>Motivated by human clicking behavior that naturally forms Gaussian distributions centered on target elements, we introduce GUI Gaussian Grounding Rewards.<n>We show that GUI-G$2$, substantially outperforms state-of-the-art method UI-TARS-72B, with the most significant improvement of 24.7% on ScreenSpot-Pro.
• Score: 51.497245303008015
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graphical User Interface (GUI) grounding maps natural language instructions to precise interface locations for autonomous interaction. Current reinforcement learning approaches use binary rewards that treat elements as hit-or-miss targets, creating sparse signals that ignore the continuous nature of spatial interactions. Motivated by human clicking behavior that naturally forms Gaussian distributions centered on target elements, we introduce GUI Gaussian Grounding Rewards (GUI-G$^2$), a principled reward framework that models GUI elements as continuous Gaussian distributions across the interface plane. GUI-G$^2$ incorporates two synergistic mechanisms: Gaussian point rewards model precise localization through exponentially decaying distributions centered on element centroids, while coverage rewards assess spatial alignment by measuring the overlap between predicted Gaussian distributions and target regions. To handle diverse element scales, we develop an adaptive variance mechanism that calibrates reward distributions based on element dimensions. This framework transforms GUI grounding from sparse binary classification to dense continuous optimization, where Gaussian distributions generate rich gradient signals that guide models toward optimal interaction positions. Extensive experiments across ScreenSpot, ScreenSpot-v2, and ScreenSpot-Pro benchmarks demonstrate that GUI-G$^2$, substantially outperforms state-of-the-art method UI-TARS-72B, with the most significant improvement of 24.7% on ScreenSpot-Pro. Our analysis reveals that continuous modeling provides superior robustness to interface variations and enhanced generalization to unseen layouts, establishing a new paradigm for spatial reasoning in GUI interaction tasks.

Related papers

• Test-Time Reinforcement Learning for GUI Grounding via Region Consistency [17.954613936413942]
  We propose a test-time scaling method that constructs spatial voting grids from multiple sampled predictions to identify consensus regions.<n>We also introduce GUI-RCPO, which transforms these consistency patterns into rewards for test-time reinforcement learning.<n>Our approach reveals the untapped potential of test-time scaling and test-time reinforcement learning for GUI grounding, offering a promising path toward more robust and data-efficient GUI agents.
  arXiv  Detail & Related papers  (2025-08-07T17:54:27Z)
• AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing [12.988814956246033]
  3D Gaussian Splatting (3DGS) has witnessed exponential adoption across diverse applications, driving a critical need for semantic-aware representations.<n>Existing approaches typically attach semantic features to a collection of free Gaussians and distill the features via differentiable rendering.<n>We introduce AG$2$aussian, a novel framework that leverages an anchor-graph structure to organize semantic features and regulate Gaussian primitives.
  arXiv  Detail & Related papers  (2025-08-03T12:47:30Z)
• R-VLM: Region-Aware Vision Language Model for Precise GUI Grounding [18.100091500983044]
  A critical challenge in GUI automation is the precise grounding of interface elements across diverse platforms.<n>Existing vision-only GUI agents directly ground elements from large and cluttered screenshots.<n>We introduce R-VLM, a novel GUI grounding approach that leverages zoomed-in region proposals for precise element localization.
  arXiv  Detail & Related papers  (2025-07-08T04:56:57Z)
• DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning [52.37530640460363]
  We introduce DiMo-GUI, a training-free framework for GUI grounding.<n>Instead of treating the GUI as a monolithic image, our method splits the input into textual elements and iconic elements.<n>When predictions are ambiguous or incorrect, DiMo-GUI dynamically focuses attention by generating candidate focal regions.
  arXiv  Detail & Related papers  (2025-06-12T03:13:21Z)
• UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents [37.871793585090586]
  We introduce UI-Genie, a self-improving framework addressing two key challenges in GUI agents.<n> verification of trajectory outcome is challenging and high-quality training data are not scalable.<n>We show that UI-Genie achieves state-of-the-art performance across multiple GUI agent benchmarks.
  arXiv  Detail & Related papers  (2025-05-27T17:58:06Z)
• GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents [13.415165482033395]
  Out-of-distribution (OOD) instructions that violate environmental constraints or exceed the current capabilities of GUI agents may suffer task breakdowns or pose security threats.<n>Traditional OOD detection methods perform suboptimally in this domain due to the complex embedding space and evolving GUI environments.<n>We propose GEM, a novel method based on fitting a Gaussian mixture model over input embedding distances extracted from the GUI Agent that reflect its capability boundary.
  arXiv  Detail & Related papers  (2025-05-19T08:29:05Z)
• GaussianGraph: 3D Gaussian-based Scene Graph Generation for Open-world Scene Understanding [20.578106363482018]
  We propose a novel framework that enhances 3DGS-based scene understanding by integrating semantic clustering and scene graph generation.<n>We introduce a "Control-Follow" clustering strategy, which dynamically adapts to scene scale and feature distribution, avoiding feature compression.<n>We enrich scene representation by integrating object attributes and spatial relations extracted from 2D foundation models.
  arXiv  Detail & Related papers  (2025-03-06T02:36:59Z)
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents [58.18100825673032]
  This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions.<n>In the OSWorld benchmark, UI-TARS achieves scores of 24.6 with 50 steps and 22.7 with 15 steps, outperforming Claude (22.0 and 14.9 respectively)
  arXiv  Detail & Related papers  (2025-01-21T17:48:10Z)
• A Geometry-Aware Message Passing Neural Network for Modeling Aerodynamics over Airfoils [61.60175086194333]
  aerodynamics is a key problem in aerospace engineering, often involving flows interacting with solid objects such as airfoils.<n>Here, we consider modeling of incompressible flows over solid objects, wherein geometric structures are a key factor in determining aerodynamics.<n>To effectively incorporate geometries, we propose a message passing scheme that efficiently and expressively integrates the airfoil shape with the mesh representation.<n>These design choices lead to a purely data-driven machine learning framework known as GeoMPNN, which won the Best Student Submission award at the NeurIPS 2024 ML4CFD Competition, placing 4th overall.
  arXiv  Detail & Related papers  (2024-12-12T16:05:39Z)
• ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining [104.34751911174196]
  We build a large-scale dataset of 3DGS using ShapeNet and ModelNet datasets. Our dataset ShapeSplat consists of 65K objects from 87 unique categories. We introduce textbftextitGaussian-MAE, which highlights the unique benefits of representation learning from Gaussian parameters.
  arXiv  Detail & Related papers  (2024-08-20T14:49:14Z)
• Spatial-spectral Hyperspectral Image Classification via Multiple Random Anchor Graphs Ensemble Learning [88.60285937702304]
  This paper proposes a novel spatial-spectral HSI classification method via multiple random anchor graphs ensemble learning (RAGE) Firstly, the local binary pattern is adopted to extract the more descriptive features on each selected band, which preserves local structures and subtle changes of a region. Secondly, the adaptive neighbors assignment is introduced in the construction of anchor graph, to reduce the computational complexity.
  arXiv  Detail & Related papers  (2021-03-25T09:31:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.