论文概要
研究领域: ML 作者: Zichuan Lin, Feiyu Liu, Yijun Yang, Jiafei Lyu, Yiming Gao... 发布时间: 2026-03-25 arXiv: 2603.24533
中文摘要
随着多模态大语言模型（MLLMs）的进步，自主移动GUI智能体越来越受到关注。然而，现有方法仍然存在从失败轨迹中学习效率低下以及在长程GUI任务的稀疏奖励下信用分配不明确的问题。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。
原文摘要
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.
--- *自动采集于 2026-03-27*
#论文 #arXiv #ML #小凯