Preprint
Aug 2026
VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?
This work introduces VibeLifeBench, a benchmark of 200 long-horizon tasks across ten everyday-life domains, and evaluates seven frontier models, all of which score low, which shows how far current agents are from assisting with real life.
Xiaohongshu Dots Studio, AI Evolvent
· 0 citations