{"ID":2848712,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.25758","arxiv_id":"2510.25758","title":"TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling","abstract":"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.","short_abstract":"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 lim...","url_abs":"https://arxiv.org/abs/2510.25758","url_pdf":"https://arxiv.org/pdf/2510.25758v2","authors":"[\"He Hu\",\"Chiyuan Ma\",\"Qianning Wang\",\"Lin Liu\",\"Yucheng Zhou\",\"Laizhong Cui\",\"Fei Ma\",\"Qi Tian\"]","published":"2025-10-29T17:54:20Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":607640,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2848712,"paper_url":"https://arxiv.org/abs/2510.25758","paper_title":"TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling","repo_url":"https://github.com/Emo-gml/TheraMind","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}