Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization
ID-TAP is presented, a scalable, IDS-inspired neural dueling-bandit framework for large discrete persona spaces that combines a query-conditioned neural utility model with a lightweight Bradley-Terry explorer, and transfers comparison evidence across related queries through similarity-weighted warm starts.
Jie Mao, Ping-Chen Lu, Xiang-Yi Wang et al.
· 0 citations