一作ACL 2026Findings· Findings of ACL
L ife S im: Long-Horizon User Life Simulator for Personalized Assistant Evaluation
Feiyu Duan · Xuanjing Huang · zhongyu wei
摘要
The rapid advancement of large language models (LLMs) has accelerated progress toward universal AI assistants. However, existing benchmarks for personalized assistants remain misaligned with real-world user-assistant interactions, failing to capture the complexity of external contexts and users’...