DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling

To advance personalized applications such as recommendation systems and user behavior prediction, recent research increasingly adopts large language models (LLMs) for humanreadable persona modeling. In dynamic realworld scenarios, effective persona modeling necessitates leveraging streaming behavior data to continually optimize user personas. However, existing methods-whether regenerating personas or incrementally extending them with new behaviors-often fail to achieve sustained improvements in persona quality or future behavior prediction accuracy. To address this, we propose DEEPER, a novel approach for dynamic persona modeling that enables continual persona optimization. Specifically, we enhance the model's direction-search capability through an iterative offline reinforcement learning framework, allowing it to automatically identify effective update directions and optimize personas using discrepancies between user behaviors and model predictions. Extensive experiments on dynamic persona modeling involving 4,800 users across 10 domains highlight DEEPER 's superior persona optimization capabilities, delivering an impressive 32.2% average reduction in user behavior prediction error over four update rounds-outperforming the best baseline by a remarkable 22.92%. 1 Recent studies increasingly utilize Large Language Models (LLMs) (OpenAI, 2023a; Anthropic, 2024; AI@Meta, 2024) for human-readable and interpretable persona modeling, advancing personalized applications like recommendation and behavior prediction. However, most research focuses on generating personas from static historical data, which fail