1
How Mobile World Model Guides GUI Agents?
探索移动GUI代理的世界模型，提升长时程交互中行动后果的预测可靠性。
arXiv:2605.10347v2 Announce Type: replace Abstract: Recent advances in vision-language models have enabled mobile GUI agents to perceive visual interf…
2
ScreenSearch: Uncertainty-Aware OS Exploration
桌面GUI代理如何应对部分可观测性？ScreenSearch用不确定性感知探索方法，提升状态探索效率。
arXiv:2605.16024v1 Announce Type: new Abstract: Desktop GUI agents operate under partial observability: visually similar screens can correspond to dif…