See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
看见、思考、行动:通过识别切换器教多模态代理有效交互GUI
机构 * School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院)
专题命中 多模态Agent :multimodal(title,abstract);分类 cs.CL、cs.AI
AI总结 本文提出State-aware Reasoning方法,通过识别当前切换状态和指令目标状态,提升多模态代理在GUI切换指令执行的准确性,实验显示准确率提升超30%。
Comments Accepted at CVPR 2026