# TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling arXiv: https://arxiv.org/abs/2510.25758 ยท HTML: https://mlsanity.com/paper/2510.25758/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. - Builds on 23 of its 109 references that are in the map. - First posted on arXiv 29 Oct 2025. ## Placed in - LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/) ## Builds on (most cited first, 23 of 23) - [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024) - [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018) - [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025) - [CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling](https://mlsanity.com/paper/2405.16433/) (2024) - [A Closer Look at the Limitations of Instruction Tuning](https://mlsanity.com/paper/2402.05119/) (2024) - [Thread of Thought Unraveling Chaotic Contexts](https://mlsanity.com/paper/2311.08734/) (2023) - [Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory](https://mlsanity.com/paper/2407.03103/) (2024) - [ESCoT: Towards Interpretable Emotional Support Dialogue Systems](https://mlsanity.com/paper/2406.10960/) (2024) - [Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions](https://mlsanity.com/paper/2408.15787/) (2024) - [MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration](https://mlsanity.com/paper/2506.19835/) (2025) - [PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counseling](https://mlsanity.com/paper/2412.13660/) (2024) - [MemoryMamba: Memory-Augmented State Space Model for Defect Recognition](https://mlsanity.com/paper/2405.03673/) (2024) - [SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agent](https://mlsanity.com/paper/2412.08389/) (2024) - [AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation](https://mlsanity.com/paper/2506.00551/) (2025) - [Speaker Turn Modeling for Dialogue Act Classification](https://mlsanity.com/paper/2109.05056/) (2021) - [Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling](https://mlsanity.com/paper/2505.15715/) (2025) - [MAGI: Multi-Agent Guided Interview for Psychiatric Assessment](https://mlsanity.com/paper/2504.18260/) (2025) - [KokoroChat: A Japanese Psychological Counseling Dialogue Dataset Collected via Role-Playing by Trained Counselors](https://mlsanity.com/paper/2506.01357/) (2025) - [AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological Counseling](https://mlsanity.com/paper/2501.09426/) (2025) - [Preference Learning Unlocks LLMs' Psycho-Counseling Skills](https://mlsanity.com/paper/2502.19731/) (2025) - [Psi-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedback](https://mlsanity.com/paper/2505.03293/) (2025) - [MIND: Towards Immersive Psychological Healing with Multi-agent Inner Dialogue](https://mlsanity.com/paper/2502.19860/) (2025) - [PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning](https://mlsanity.com/paper/2508.09521/) (2025) ## Built on by (most cited first, 7 of 7) - [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026) - [Demystifying Low-Rank Knowledge Distillation in Large Language Models: Convergence, Generalization, and Information-Theoretic Guarantees](https://mlsanity.com/paper/2603.22355/) (2026) - [DMT-CBT: Longitudinal Therapeutic State Modeling for CBT Counseling](https://mlsanity.com/paper/2606.03132/) (2026) - [AE-LLM: Adaptive Efficiency Optimization for Large Language Models](https://mlsanity.com/paper/2603.20492/) (2026) - [EmoTrace: An Emotion Trajectory-Centered Framework for Psychological Support Dialogue Generation](https://mlsanity.com/paper/2607.23648/) (2026) - [FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue](https://mlsanity.com/paper/2608.16303/) (2026) - [From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health](https://mlsanity.com/paper/2609.25186/) (2026) ## Abstract (arXiv) 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.