Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents 文章
ArXiv CS.AI2026-08-05PAPERen作者: Siqi Fan, Minghao Li, Xiaoqian Ma, Wenhui Tan, Xiusheng Huang, Juntong Wu, Liujie Zhang, Shuo Shang, Weihang Chen