Mobile-Agent-V: Learning Mobile Device Operation Through Video-Guided Multi-Agent Collaboration
Paper
•
2502.17110
•
Published
•
10
GUI-Agent
GUI Agent相关论文方案简要分析
Note Mobile,Alibaba,one-shot 通过对操作视频处理提取关键帧长图作为后续动作推理的实例 推理过程通过推理、反思、critile 提升推理动作质量