# GUI-C2: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning arXiv: https://arxiv.org/abs/2605.30884 ยท HTML: https://mlsanity.com/paper/2605.30884/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. - Builds on 28 of its 39 references that are in the map. - First posted on arXiv 29 May 2026. ## Placed in - LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/) - LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/) ## Builds on (most cited first, 28 of 28) - [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024) - [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (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) - [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025) - [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024) - [ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use](https://mlsanity.com/paper/2504.07981/) (2025) - [GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents](https://mlsanity.com/paper/2504.10458/) (2025) - [ShowUI: One Vision-Language-Action Model for GUI Visual Agent](https://mlsanity.com/paper/2411.17465/) (2024) - [UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning](https://mlsanity.com/paper/2503.21620/) (2025) - [OpenCUA: Open Foundations for Computer-Use Agents](https://mlsanity.com/paper/2508.09123/) (2025) - [GTA1: GUI Test-time Scaling Agent](https://mlsanity.com/paper/2507.05791/) (2025) - [UIBert: Learning Generic Multimodal Representations for UI Understanding](https://mlsanity.com/paper/2107.13731/) (2021) - [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) - [Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning](https://mlsanity.com/paper/2505.12370/) (2025) - [DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning](https://mlsanity.com/paper/2507.00008/) (2025) - [LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization](https://mlsanity.com/paper/2503.08271/) (2025) - [Uncertainty-Aware GUI Agent: Adaptive Perception through Component Recommendation and Human-in-the-Loop Refinement](https://mlsanity.com/paper/2508.04025/) (2025) - [UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding](https://mlsanity.com/paper/2604.14113/) (2026) - [AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement](https://mlsanity.com/paper/2603.17441/) (2026) - [Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges](https://mlsanity.com/paper/2511.13261/) (2025) - [Zoom to Essence: Trainless GUI Grounding by Inferring upon Interface Elements](https://mlsanity.com/paper/2603.14448/) (2026) - [GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models](https://mlsanity.com/paper/2604.14262/) (2026) - [BAMI: Training-Free Bias Mitigation in GUI Grounding](https://mlsanity.com/paper/2605.06664/) (2026) - [Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units](https://mlsanity.com/paper/2508.18763/) (2025) - [Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation](https://mlsanity.com/paper/2605.12953/) (2026) ## Built on by (most cited first, 2 of 2) - [EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent](https://mlsanity.com/paper/2607.13792/) (2026) - [GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning](https://mlsanity.com/paper/2610.19100/) (2026) ## Abstract (arXiv) Existing agentic reinforcement learning methods for GUI grounding have limitations at two levels. At the data level, current approaches typically treat all training samples equally, although their training value to the baseline model varies with difficulty. Overlooking this can greatly reduce training efficiency or even cause collapse. At the strategy level, existing frameworks struggle to balance the trade-off between cropping larger regions for sufficient context and smaller ones for reduced redundancy, a tension inherent to tool-augmented grounding agents. In addition, overly complex decision-making is difficult for small-parameter models and significantly increases inference time. To address these issues, at the data level, we propose GUI-D, a data mining and difficulty scoring pipeline that identifies the training-worthy samples by proper testing and assigns difficulty scores to guide subsequent training weights. At the strategy level, we propose GUI-C2, which employs an area-gated coarse-to-fine refinement mechanism that progressively narrows the visual field via model-internal uncertainty signals, adaptively reserving context for large targets while amplifying precision for small ones, reinforced by improvement-aware stage rewards that ensure each refinement genuinely advances grounding. Meanwhile, we simplify the decision-making process to greatly reduce additional inference time. Finally, extensive experiments show that our method achieves state-of-the-art performance. The code and data will be publicly available.