GUI-ARP：通过自适应区域感知增强GUI智能体的定位能力
GUI-ARP: Enhancing Grounding with Adaptive Region Perception for GUI Agents
AI总结：
本文提出GUI-ARP框架，通过自适应区域感知与阶段控制实现动态多阶段推理，并结合GRPO强化微调，在GUI定位基准上以7B规模超越更大模型，取得最先进性能。
摘要：
现有的GUI定位方法在高分辨率截图中往往难以实现细粒度定位。为解决这一问题，我们提出GUI-ARP，一种支持自适应多阶段推理的新型框架。该框架配备所提出的自适应区域感知（ARP）和自适应阶段控制（ASC），能够动态利用视觉注意力裁剪与任务相关的区域，并调整其推理策略：对简单情况执行单阶段推理，对更复杂的场景则进行多阶段分析。这一能力通过一个两阶段训练流程实现，该流程将监督微调与基于分组相对策略优化（GRPO）的强化微调相结合。大量实验表明，所提出的GUI-ARP在具有挑战性的GUI定位基准上取得了最先进的性能，其7B模型在ScreenSpot-Pro上达到60.8%的准确率，在UI-Vision基准上达到30.9%。值得注意的是，GUI-ARP-7B展现出与开源72B模型（UI-TARS-72B为38.1%）及专有模型相抗衡的强大竞争力。
英文摘要：
Existing GUI grounding methods often struggle with fine-grained localization in high-resolution screenshots. To address this, we propose GUI-ARP, a novel framework that enables adaptive multi-stage inference. Equipped with the proposed Adaptive Region Perception (ARP) and Adaptive Stage Controlling (ASC), GUI-ARP dynamically exploits visual attention for cropping task-relevant regions and adapts its inference strategy, performing a single-stage inference for simple cases and a multi-stage analysis for more complex scenarios. This is achieved through a two-phase training pipeline that integrates supervised fine-tuning with reinforcement fine-tuning based on Group Relative Policy Optimization (GRPO). Extensive experiments demonstrate that the proposed GUI-ARP achieves state-of-the-art performance on challenging GUI grounding benchmarks, with a 7B model reaching 60.8% accuracy on ScreenSpot-Pro and 30.9% on UI-Vision benchmark. Notably, GUI-ARP-7B demonstrates strong competitiveness against open-source 72B models (UI-TARS-72B at 38.1%) and proprietary models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
