Towards Proactive Personalization through Profile Customization for Individual Users in Dialogues

TL;DR

This paper introduces PersonalAgent, a lifelong user-centric system that continuously infers and adapts to individual preferences in dialogues, improving personalization and coherence over time in interactive systems using LLMs.

Contribution

The paper presents PersonalAgent, a novel lifelong personalization framework that dynamically constructs and refines user profiles through dialogue, addressing cold-start and long-term adaptation challenges.

Findings

PersonalAgent outperforms prompt-based and policy baselines in various contexts.

It maintains preference consistency across sessions.

Human evaluation shows natural and coherent preference capturing.

Abstract

The deployment of Large Language Models (LLMs) in interactive systems necessitates a deep alignment with the nuanced and dynamic preferences of individual users. Current alignment techniques predominantly address universal human values or static, single-turn preferences, thereby failing to address the critical needs of long-term personalization and the initial user cold-start problem. To bridge this gap, we propose PersonalAgent, a novel user-centric lifelong agent designed to continuously infer and adapt to user preferences. PersonalAgent constructs and dynamically refines a unified user profile by decomposing dialogues into single-turn interactions, framing preference inference as a sequential decision-making task. Experiments show that PersonalAgent achieves superior performance over strong prompt-based and policy optimization baselines, not only in idealized but also in noisy conversational contexts, while preserving cross-session preference consistency. Furthermore, human evaluation confirms that PersonalAgent excels at capturing user preferences naturally and coherently. Our findings underscore the importance of lifelong personalization for developing more inclusive and adaptive conversational agents. Our code is available here.