Pith. sign in

REVIEW 20 cited by

GUI-G²: Gaussian Reward Modeling for GUI Grounding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2507.15846 v3 pith:MGC4C3F3 submitted 2025-07-21 cs.LG cs.AIcs.CLcs.CVcs.HC

GUI-G²: Gaussian Reward Modeling for GUI Grounding

classification cs.LG cs.AIcs.CLcs.CVcs.HC
keywords gaussiandistributionscontinuousgroundinggui-ginterfacerewardselement
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 20 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Covering Human Action Space for Computer Use: Data Synthesis and Benchmark

    cs.CV 2026-05 unverdicted novelty 7.0

    Presents CUActSpot benchmark and renderer-LLM data synthesis that lets a 4B model outperform larger open-source models on complex computer interactions.

  2. OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents

    cs.CL 2026-04 unverdicted novelty 7.0

    OS-SPEAR is a new evaluation toolkit that tests 22 OS agents and identifies trade-offs between efficiency and safety or robustness.

  3. RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management

    cs.AI 2026-04 unverdicted novelty 7.0

    RiskWebWorld is the first realistic interactive benchmark for GUI agents in e-commerce risk management, revealing a large gap between generalist and specialized models plus RL gains.

  4. UIPress: Bringing Optical Token Compression to UI-to-Code Generation

    cs.CL 2026-04 unverdicted novelty 7.0

    UIPress is the first encoder-side learned optical compression method for UI-to-Code that compresses visual tokens to 256, outperforming the uncompressed baseline by 7.5% CLIP score and the best inference-time baseline...

  5. Grounding Computer Use Agents on Human Demonstrations

    cs.LG 2025-11 conditional novelty 7.0

    GroundCUA, a 3.56M-element human-annotated desktop grounding dataset, and GroundNext models achieve strong UI grounding with less than one-tenth the SFT data of prior work.

  6. GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding

    cs.CV 2025-11 conditional novelty 7.0

    Supervising an MLLM's intrinsic self-attention with patch-level GUI labels, aggregated via a learnable anchor token and hidden-state-selected query tokens, reaches state-of-the-art 3B-scale GUI grounding accuracy with...

  7. GUI-AC: Enhancing Continual Learning in GUI Agents

    cs.CV 2026-06 conditional novelty 6.0

    Grounding-certainty-guided Adaptive Advantage and Dynamic Clipping improve continual GUI grounding over RFT baselines on ScreenSpot-V1/V2/Pro.

  8. BAMI: Training-Free Bias Mitigation in GUI Grounding

    cs.CV 2026-05 unverdicted novelty 6.0

    BAMI mitigates precision and ambiguity biases in GUI grounding via coarse-to-fine focus and candidate selection, raising accuracy on ScreenSpot-Pro without training.

  9. GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

    cs.LG 2026-02 conditional novelty 6.0

    Action-weighted SFT plus KL-regularized GRPO on a curated 81K reasoning dataset lifts open-source GUI agents by 11–22 points on online task-completion benchmarks.

  10. RISK: A Framework for GUI Agents in E-commerce Risk Management

    cs.AI 2025-09 unverdicted novelty 6.0

    RISK introduces a dataset, benchmark, and R1-style RL fine-tuning for GUI agents that achieve 6.8-8.8% offline gains and 70.5% online task success in e-commerce risk management using 7.2% of baseline parameters.

  11. VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents

    cs.CL 2025-09 unverdicted novelty 6.0

    VeriOS-Agent is an OS agent that proactively queries humans in untrustworthy scenarios via a query-driven framework and three-stage training, achieving 19.72% higher step-wise success rate over baselines while preserv...

  12. GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning

    cs.CV 2026-05 unverdicted novelty 5.0

    GUI-C² pairs a difficulty-scoring data pipeline with an area-gated coarse-to-fine RL mechanism to improve GUI grounding accuracy and training stability.

  13. Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents

    cs.CL 2026-05 unverdicted novelty 5.0

    Mobile-Aptus uses supervised fine-tuning followed by semantic similarity retrieval and direct preference optimization to calibrate confidence scores in mobile agents, yielding over 17% average task success improvement...

  14. GUI Agents with Reinforcement Learning: Toward Digital Inhabitants

    cs.AI 2026-04 unverdicted novelty 5.0

    The paper delivers the first comprehensive overview of RL for GUI agents, organizing methods into offline, online, and hybrid strategies while analyzing trends in rewards, efficiency, and deliberation to outline a fut...

  15. Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding

    cs.LG 2026-04 unverdicted novelty 5.0

    A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.

  16. PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors

    cs.CV 2026-04 conditional novelty 5.0

    Multi-turn visual feedback (red-cross markers) raises Claude Opus 4.7 text-cursor grounding from ~23% to ~48% on a 5390-sample VS Code/Cursor benchmark, while small open models gain almost nothing.

  17. PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors

    cs.CV 2026-04 unverdicted novelty 5.0

    Multi-turn visual feedback refinement outperforms single-shot coordinate prediction for pixel-precise GUI grounding in complex coding environments.

  18. Rethinking Token Pruning for Historical Screenshots in GUI Visual Agents: Semantic, Spatial, and Temporal Perspectives

    cs.CV 2026-03 unverdicted novelty 5.0

    Empirical study finds background semantics, random pruning, and recency-based allocation improve token efficiency for GUI visual agents.

  19. Enhancing Trustworthy GUI Grounding via Self-Critiqued Reinforcement Learning

    cs.CV 2025-10 conditional novelty 5.0

    HyperClick trains GUI grounding models with GRPO to output clicks plus confidence scores, jointly rewarding correct clicks and Brier-calibrated confidence, and reports SOTA accuracy on six of seven benchmarks with bet...

  20. GUI-AC: Enhancing Continual Learning in GUI Agents

    cs.CV 2026-06 unverdicted novelty 4.0

    GUI-AC stabilizes RFT for non-stationary GUI data by down-weighting noisy advantages and relaxing clipping bounds via a grounding certainty term.