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

• URL: http://arxiv.org/abs/2605.30884v1
• Date: Fri, 29 May 2026 06:17:53 GMT
• Title: GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning
• Abstract summary: GUI-D identifies training-worthy samples by proper testing and assigns difficulty scores to guide subsequent training weights.<n>At the strategy level, we propose GUI-C$2$, which employs an area-gated coarse-to-fine refinement mechanism.<n>Our method achieves state-of-the-art performance.
• Score: 23.582549876926432
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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-C$^2$, 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.

Related papers

• Focus When Necessary: Adaptive Routing and Collaborative Grounding for Training-Free Visual Grounding [56.38477453373368]
  LazyMCoT is a dynamic and training-free framework that adaptively allocates visual grounding efforts based on sample difficulty.<n>LazyMCoT rivals training-based approaches by simultaneously improving reasoning accuracy and reducing average inference latency.
  arXiv  Detail & Related papers  (2026-06-15T03:17:44Z)
• GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL [64.8155693023222]
  Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks.<n>This gap stems from a shortage of high-quality, action-aligned reasoning data.<n>We present GUI-Libra, a tailored training recipe that addresses these challenges.
  arXiv  Detail & Related papers  (2026-02-25T18:34:57Z)
• Learning with Challenges: Adaptive Difficulty-Aware Data Generation for Mobile GUI Agent Training [10.376682582953046]
  MobileGen is a novel data generation framework that aligns training difficulty with the GUI agent's capability frontier.<n>It consistently outperforms existing data generation methods by improving the average performance of GUI agents by 1.57 times.<n>This highlights the importance of capability-aligned data generation for effective mobile GUI agent training.
  arXiv  Detail & Related papers  (2026-01-30T10:03:20Z)
• Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data [89.96277093034547]
  We introduce EntroDrop, an entropy-guided token dropout method that functions as structured data regularization.<n>We show that EntroDrop consistently outperforms standard regularization baselines and maintains robust performance throughout extended multi-epoch training.
  arXiv  Detail & Related papers  (2025-12-29T12:35:51Z)
• CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks [11.121687042616974]
  Reinforcement Learning (RL) can effectively enhance agents' performance in dynamic interactive GUI environments.<n>Most approaches collapse task-specific nuances into a single, coarse reward, leaving the agent with a uniform signal that yields inefficient policy updates.<n>We propose CRAFT-GUI, a curriculum learning framework based on Group Relative Policy Optimization (GRPO) that explicitly accounts for the varying difficulty across trajectories.
  arXiv  Detail & Related papers  (2025-08-15T09:55:02Z)
• UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding [16.939058522414836]
  We introduce UI-AGILE for enhancing GUI agents at both training and inference.<n>For training, we propose a suite of improvements to the Supervised Fine-Tuning (SFT) process.<n>For inference, we present decomposed grounding with selection to dramatically improve grounding accuracy on high-resolution displays.
  arXiv  Detail & Related papers  (2025-07-29T17:22:07Z)
• Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning [69.64809103333839]
  We investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reasoning.<n>Our approach demonstrates significant performances across various multi-modal mathematical reasoning benchmarks with only 2K+0.6K two-stage training data.
  arXiv  Detail & Related papers  (2025-05-19T15:43:10Z)
• Improving Long-Horizon Imitation Through Instruction Prediction [93.47416552953075]
  In this work, we explore the use of an often unused source of auxiliary supervision: language. Inspired by recent advances in transformer-based models, we train agents with an instruction prediction loss that encourages learning temporally extended representations that operate at a high level of abstraction. In further analysis we find that instruction modeling is most important for tasks that require complex reasoning, while understandably offering smaller gains in environments that require simple plans.
  arXiv  Detail & Related papers  (2023-06-21T20:47:23Z)
• Some like it tough: Improving model generalization via progressively increasing the training difficulty [3.04585143845864]
  We propose to progressively increase the training difficulty during learning a neural network model via a novel strategy. This strategy makes sure that the puts its focus in the later training stages on the more difficult samples. Experiments on several image classification problems show that mini-batch trimming is able to increase the generalization ability.
  arXiv  Detail & Related papers  (2021-10-25T15:54:21Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• Improving Semantic Segmentation via Self-Training [75.07114899941095]
  We show that we can obtain state-of-the-art results using a semi-supervised approach, specifically a self-training paradigm. We first train a teacher model on labeled data, and then generate pseudo labels on a large set of unlabeled data. Our robust training framework can digest human-annotated and pseudo labels jointly and achieve top performances on Cityscapes, CamVid and KITTI datasets.
  arXiv  Detail & Related papers  (2020-04-30T17:09:17Z)

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.