Latent Preference Modeling for Multi-Session Personalized Tool Calling
This work presents Multi-Session Personalized Tool Calling (MPT), a benchmark comprising 4,695 instances over 459 multi-session interaction histories that cover three challenges: Preference Recall, Induction, and Transfer, and proposes PRefine, a test-time memory method that maintains the user's latent preference as a...
Yejin Yoon, Minseon Kim, Taeuk Kim
· 2 citations