TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hu, He, Ma, Chiyuan, Wang, Qianning, Liu, Lin, Zhou, Yucheng, Cui, Laizhong, Ma, Fei, Tian, Qi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910056834924544
author Hu, He
Ma, Chiyuan
Wang, Qianning
Liu, Lin
Zhou, Yucheng
Cui, Laizhong
Ma, Fei
Tian, Qi
author_facet Hu, He
Ma, Chiyuan
Wang, Qianning
Liu, Lin
Zhou, Yucheng
Cui, Laizhong
Ma, Fei
Tian, Qi
contents The shortage of mental health professionals has driven the web to become a primary avenue for accessible psychological support. While Large Language Models (LLMs) offer promise for scalable web-based counseling, existing approaches often lack emotional understanding, adaptive strategies, and long-term memory. These limitations pose risks to digital well-being, as disjointed interactions can fail to support vulnerable users effectively. To address these gaps, we introduce TheraMind, a strategic and adaptive agent designed for trustworthy online longitudinal counseling. The cornerstone of TheraMind is a novel dual-loop architecture that decouples the complex counseling process into an Intra-Session Loop for tactical dialogue management and a Cross-Session Loop for strategic therapeutic planning. The Intra-Session Loop perceives the patient's emotional state to dynamically select response strategies while leveraging cross-session memory to ensure continuity. Crucially, the Cross-Session Loop empowers the agent with long-term adaptability by evaluating the efficacy of the applied therapy after each session and adjusting the method for subsequent interactions. We validate our approach in a high-fidelity simulation environment grounded in real clinical cases. Extensive evaluations show that TheraMind outperforms other methods, especially on multi-session metrics like Coherence, Flexibility, and Therapeutic Attunement, validating the effectiveness of its dual-loop design in emulating strategic, adaptive, and longitudinal therapeutic behavior. The code is publicly available at https://github.com/Emo-gml/TheraMind.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25758
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling
Hu, He
Ma, Chiyuan
Wang, Qianning
Liu, Lin
Zhou, Yucheng
Cui, Laizhong
Ma, Fei
Tian, Qi
Artificial Intelligence
The shortage of mental health professionals has driven the web to become a primary avenue for accessible psychological support. While Large Language Models (LLMs) offer promise for scalable web-based counseling, existing approaches often lack emotional understanding, adaptive strategies, and long-term memory. These limitations pose risks to digital well-being, as disjointed interactions can fail to support vulnerable users effectively. To address these gaps, we introduce TheraMind, a strategic and adaptive agent designed for trustworthy online longitudinal counseling. The cornerstone of TheraMind is a novel dual-loop architecture that decouples the complex counseling process into an Intra-Session Loop for tactical dialogue management and a Cross-Session Loop for strategic therapeutic planning. The Intra-Session Loop perceives the patient's emotional state to dynamically select response strategies while leveraging cross-session memory to ensure continuity. Crucially, the Cross-Session Loop empowers the agent with long-term adaptability by evaluating the efficacy of the applied therapy after each session and adjusting the method for subsequent interactions. We validate our approach in a high-fidelity simulation environment grounded in real clinical cases. Extensive evaluations show that TheraMind outperforms other methods, especially on multi-session metrics like Coherence, Flexibility, and Therapeutic Attunement, validating the effectiveness of its dual-loop design in emulating strategic, adaptive, and longitudinal therapeutic behavior. The code is publicly available at https://github.com/Emo-gml/TheraMind.
title TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling
topic Artificial Intelligence
url https://arxiv.org/abs/2510.25758