Existing methods for AI psychological counselors predominantly rely on supervised fine-tuning using static dialogue datasets. However, this contrasts with human experts, who continuously refine their proficiency through clinical practice and accumulated experience. To bridge this gap, we propose an Experience-Driven Lifelong Learning Agent (\texttt{PsychAgent}) for psychological counseling. First, we establish a Memory-Augmented Planning Engine tailored for longitudinal multi-session interactions, which ensures therapeutic continuity through persistent memory and strategic planning. Second, to support self-evolution, we design a Skill Evolution Engine that extracts new practice-grounded skills from historical counseling trajectories. Finally, we introduce a Reinforced Internalization Engine that integrates the evolved skills into the model via rejection fine-tuning, aiming to improve performance across diverse scenarios. Comparative analysis shows that our approach achieves higher scores than strong general LLMs (e.g., GPT-5.4, Gemini-3) and domain-specific baselines across all reported evaluation dimensions. These results suggest that lifelong learning can improve the consistency and overall quality of multi-session counseling responses.
@article{arxiv.2604.00931,
title = {PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor},
author = {Yutao Yang and Junsong Li and Qianjun Pan and Jie Zhou and Kai Chen and Qin Chen and Jingyuan Zhao and Ningning Zhou and Xin Li and Liang He},
journal= {arXiv preprint arXiv:2604.00931},
year = {2026}
}