AI RESEARCH
User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction
arXiv CS.AI
•
ArXi:2603.20939v1 Announce Type: cross Large language models are increasingly used as personal assistants, yet most lack a persistent user model, forcing users to repeatedly restate preferences across sessions. We propose Vector-Adapted Retrieval Scoring (VARS), a pipeline-agnostic, frozen-backbone framework that represents each user with long-term and short-term vectors in a shared preference space and uses these vectors to bias retrieval scoring over structured preference memory.