AI RESEARCH
Quick on the Uptake: Eliciting Implicit Intents from Human Demonstrations for Personalized Mobile-Use Agents
arXiv CS.CL
•
ArXi:2508.08645v2 Announce Type: replace As multimodal large language models advance rapidly, the automation of mobile tasks has become increasingly feasible through the use of mobile-use agents that mimic human interactions from graphical user interface. To further enhance mobile-use agents, previous studies employ nstration learning to improve mobile-use agents from human nstrations.