Author name: Daiqiang Li, Zihao Pan, Zeyu Zhang, Ronghao Chen, Huacan Wang, Honggang Chen, Haiyun Jiang

arXiv:2603.26041v2 Announce Type: replace
Abstract: In recent years, GUI visual agents built upon Multimodal Large Language Models (MLLMs) have demonstrated strong potential in navigation tasks. However, high-resolution GUI screenshots produce a large…

arXiv:2603.26041v1 Announce Type: new
Abstract: In recent years, GUI visual agents built upon Multimodal Large Language Models (MLLMs) have demonstrated strong potential in navigation tasks. However, high-resolution GUI screenshots produce a large num…