作者位次 #9/11ACL 2026Poster· Natural Language Processing
I nquire M obile: Teaching VLM -based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning
Qihang Ai · Pi Bu · Yue Cao · Yingyao Wang · Jihao Gu · Jingxuan Xing · Zekun Zhu · Wei Jiang · Zhicheng Zheng · Jun Song · Yuning Jiang (Taobao &
摘要
Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions. However, the current fully autonomous paradigm poses potential safety risks when model understanding or reasoning capabilities are...