Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by several critical challenges: data bottleneck in end-to-end training, high cost of delayed error detection, and risk of contradictory guidance. Inspired by the human cognitive loop of Thinking, Alignment, and Reflection, we present D-Artemis -- a novel deliberative framework in this paper. D-Artemis leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process. It also employs a proactive Pre-execution Alignment stage, where Thought-Action Consistency (TAC) Check module and Action Correction Agent (ACA) work in concert to mitigate the risk of execution failures. A post-execution Status Reflection Agent (SRA) completes the cognitive loop, enabling strategic learning from experience. Crucially, D-Artemis enhances the capabilities of general-purpose Multimodal large language models (MLLMs) for GUI tasks without the need for training on complex trajectory datasets, demonstrating strong generalization. D-Artemis establishes new state-of-the-art (SOTA) results across both major benchmarks, achieving a 75.8% success rate on AndroidWorld and 96.8% on ScreenSpot-V2. Extensive ablation studies further demonstrate the significant contribution of each component to the framework.

翻译：图形用户界面（GUI）智能体旨在通过模拟用户交互来自动化广泛的人类任务。尽管进展迅速，但当前方法仍受限于几个关键挑战：端到端训练中的数据瓶颈、延迟错误检测的高成本以及矛盾指令的风险。受人类“思考、对齐与反思”认知循环的启发，本文提出了D-Artemis——一种新颖的审慎框架。D-Artemis利用细粒度的、特定于应用程序的提示检索机制来为其决策过程提供信息。它还采用主动的预执行对齐阶段，其中“思想-行动一致性”（TAC）检查模块与行动校正智能体（ACA）协同工作，以降低执行失败的风险。执行后的状态反思智能体（SRA）则完成了认知循环，实现了从经验中进行策略性学习。至关重要的是，D-Artemis增强了通用多模态大语言模型（MLLMs）处理GUI任务的能力，而无需在复杂的轨迹数据集上进行训练，展现了强大的泛化能力。D-Artemis在两大主要基准测试中均取得了新的最先进（SOTA）成果，在AndroidWorld上实现了75.8%的成功率，在ScreenSpot-V2上实现了96.8%的成功率。广泛的消融研究进一步证明了框架中每个组件的重要贡献。