PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915961794199552 |
|---|---|
| author | Yang, Yutao Li, Junsong Pan, Qianjun Zhou, Jie Chen, Kai Chen, Qin Zhao, Jingyuan Zhou, Ningning Li, Xin He, Liang |
| author_facet | Yang, Yutao Li, Junsong Pan, Qianjun Zhou, Jie Chen, Kai Chen, Qin Zhao, Jingyuan Zhou, Ningning Li, Xin He, Liang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00931 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor Yang, Yutao Li, Junsong Pan, Qianjun Zhou, Jie Chen, Kai Chen, Qin Zhao, Jingyuan Zhou, Ningning Li, Xin He, Liang Artificial Intelligence 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. |
| title | PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.00931 |