Paper Detail
Yutao Yang, Junsong Li, Qianjun Pan, Jie Zhou, Kai Chen, Qin Chen, Jingyuan Zhao, Ningning Zhou, Xin Li, Liang He
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{yang2026psychagent,
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},
year = {2026},
abstract = {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 (\textbackslash{}texttt\{PsychAgent\}) for psychological counseling. First, we establish a Memory-Augmented Planning Engine tailored for longitudinal multi-session interaction},
url = {https://arxiv.org/abs/2604.00931},
keywords = {cs.AI},
eprint = {2604.00931},
archiveprefix = {arXiv},
}
{}