Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous credit assignment under sparse rewards for long-horizon GUI tasks. To that end, we propose UI-Voyager, a novel two-stage self-evolving mobile GUI agent. In the first stage, we employ Rejection Fine-Tuning (RFT), which enables the continuous co-evolution of data and models in a fully autonomous loop. The second stage introduces Group Relative Self-Distillation (GRSD), which identifies critical fork points in group rollouts and constructs dense step-level supervision from successful trajectories to correct failed ones. Extensive experiments on AndroidWorld show that our 4B model achieves an 81.0% Pass@1 success rate, outperforming numerous recent baselines and exceeding human-level performance. Ablation and case studies further verify the effectiveness of GRSD. Our method represents a significant leap toward efficient, self-evolving, and high-performance mobile GUI automation without expensive manual data annotation.

翻译：自主移动GUI智能体随着多模态大语言模型（MLLM）的发展日益受到关注。然而，现有方法在长时域GUI任务中仍面临失败轨迹学习效率低下、稀疏奖励条件下信用分配模糊等挑战。为此，我们提出UI-Voyager——一种新颖的两阶段自进化移动GUI智能体。第一阶段采用拒绝微调（RFT）技术，在完全自驱动循环中实现数据与模型的持续协同进化。第二阶段引入组相对自蒸馏（GRSD），通过识别群体轨迹中的关键分叉点，从成功轨迹中构建密集的步骤级监督信号以纠正失败轨迹。在AndroidWorld上的大量实验表明，我们的4B模型实现了81.0%的Pass@1成功率，超越了多个最新基线方法并达到人类水平。消融实验与案例研究进一步验证了GRSD的有效性。本方法为无需昂贵人工数据标注的高效自进化高性能移动GUI自动化开辟了新路径。