Preprint
Aug 2026
SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information
SPIEval is introduced, a human-curated benchmark grounded in five cognitive capabilities that exposes fundamental limitations of current LLM-based mobile assistants and motivates future research in this direction.
Junjie Ye, Zhuohui Sheng, Shao-Hua Liu et al.
· 0 citations