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

arXiv: https://arxiv.org/abs/2502.11078 · HTML: https://mlsanity.com/paper/2502.11078/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2025.

## Built on by (most cited first, 10 of 10)

- [Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation](https://mlsanity.com/paper/2512.06690/) (2025)
- [Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment](https://mlsanity.com/paper/2505.15456/) (2025)
- [AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery](https://mlsanity.com/paper/2604.05550/) (2026)
- [Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation](https://mlsanity.com/paper/2606.03866/) (2026)
- [CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factors](https://mlsanity.com/paper/2604.14773/) (2026)
- [PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue](https://mlsanity.com/paper/2608.06975/) (2026)
- [Hierarchical Multi-Persona Induction from User Behavioral Logs: Learning Evidence-Grounded and Truthful Personas](https://mlsanity.com/paper/2604.26120/) (2026)
- [From Empathy to Personalized Empathy: Adapting Empathetic Strategies to Individual Users](https://mlsanity.com/paper/2606.00728/) (2026)
- [Toward Human-Centered Multi-Agent Systems: Integrating Cognition, Culture, Values, and Cooperation in AI Agents](https://mlsanity.com/paper/2606.08274/) (2026)
- [Vela: User Behavior as Supervision Sparks LLM Intelligence](https://mlsanity.com/paper/2610.14709/) (2026)

## Abstract (arXiv)

To advance personalized applications such as recommendation systems and user behavior prediction, recent research increasingly adopts large language models (LLMs) for human -readable persona modeling. In dynamic real -world 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 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 4800 users across 10 domains highlight the superior persona optimization capabilities of DEEPER, 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%.