What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning 文章

ArXiv CS.AI2026-06-02NEWSen作者: Songze Li, Xiaoke Guo, Tianqi Liu, Biao Yi, Zhaoyan Gong, Zhiqiang Liu, Huajun Chen, Wen Zhang
大语言模型
查看原文 →
关系图谱

What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning · 相关技术

相关技术

UI Comprehension taskUI-in-the-LoopMultimodal Large Language Models (MLLMs)UI-in-the-Loop (UILoop)