Current GUI agents have achieved outstanding performance in GUI element grounding. However, planning remains highly challenging, especially due to sensitivity to the initial state of the environment. Specifically, slight differences in the initial state-such as the target software not being open or the interface not being in its default state-often lead to planning errors. This issue is widespread in real user scenarios, but existing benchmarks fail to evaluate it. In this paper, we present WorldGUI, a novel GUI benchmark that designs GUI tasks with various initial states to simulate real computer-user interactions. The benchmark spans a wide range of tasks across 10 popular software applications, including PowerPoint, VSCode, and Adobe Acrobat. In addition, to address the challenges of dynamic GUI automation tasks, we propose GUI-Thinker, a holistic framework, leveraging a critique mechanism, that effectively manages the unpredictability and complexity of GUI interactions. Experimental results demonstrate that GUI-Thinker significantly outperforms Claude-3.5 (Computer Use) by 14.9% in success rate on WorldGUI tasks. This improvement underscores the effectiveness of our critical-thinking-based framework in enhancing GUI automation.

翻译：当前图形用户界面智能体在界面元素定位方面已取得卓越性能。然而，任务规划仍面临巨大挑战，尤其是其对环境初始状态的高度敏感性。具体而言，初始状态的细微差异——例如目标软件未启动或界面未处于默认状态——常导致规划错误。该问题在真实用户场景中普遍存在，但现有基准测试未能有效评估此现象。本文提出WorldGUI这一新型图形用户界面基准测试，通过设计具有多样化初始状态的界面任务来模拟真实的计算机用户交互。该基准涵盖10款主流软件应用程序的广泛任务场景，包括PowerPoint、VSCode和Adobe Acrobat等。此外，为应对动态图形用户界面自动化任务的挑战，我们提出GUI-Thinker整体框架，该框架通过批判性反思机制有效管理图形用户界面交互的不确定性与复杂性。实验结果表明，在WorldGUI任务中，GUI-Thinker的成功率较Claude-3.5（计算机使用）显著提升14.9%。这一改进凸显了我们基于批判性思维框架在增强图形用户界面自动化方面的有效性。