collaborators

1 paper

cs.HC2026

After Talking with 1,000 Personas: Learning Preference-Aligned Proactive Assistants From Large-Scale Persona Interactions

Ziyi Xuan, Yiwen Wu, Zhaoyang Yan +2

Smart assistants increasingly act proactively, yet mistimed or intrusive behavior often causes users to lose trust and disable these features. Learning user preferences for proacti…