DeepSAGE: Stage-Aware Reinforcement Learning for Structured CBT Counseling Dialogue

• URL: http://arxiv.org/abs/2608.22615v1
• Date: Sun, 23 Aug 2026 21:40:58 GMT
• Title: DeepSAGE: Stage-Aware Reinforcement Learning for Structured CBT Counseling Dialogue
• Abstract summary: We present DeepSAGE, a framework for stage-aware counseling dialogue grounded in Cognitive Behavioral Therapy (CBT)<n>DeepSAGE represents the session as eleven stages with explicit therapeutic objectives, with an external controller determines stage completion.<n>DeepSAGE elicits higher simulated client engagement and openness and achieves the strongest balance of stage-goal completion and dialogue efficiency.
• Score: 44.08107411670182
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Model (LLM)-based counseling agents can generate fluent and supportive responses, but they often lack the structured, goal-directed progression required to conduct a coherent therapeutic session. We present DeepSAGE (Strategic AI Guidance Engine), a hybrid LLM--Deep Reinforcement Learning (DRL) framework for stage-aware counseling dialogue grounded in the first session of Cognitive Behavioral Therapy (CBT). DeepSAGE represents the session as eleven stages with explicit therapeutic objectives, with an external controller determines stage completion and the DRL model selects therapeutic intentions that guide LLM response generation. We evaluate DeepSAGE against six retrieval-, prompting-, stage-, and policy-based alternatives. DeepSAGE elicits higher simulated client engagement and openness and achieves the strongest balance of stage-goal completion and dialogue efficiency among stage-structured systems. Domain expert review further indicates that the generated conversations exhibit broadly plausible emotional trajectories and recognizable CBT processes. Because the evaluation relies primarily on simulated clients and model-based metrics, these findings demonstrate comparative dialogue-control improvements rather than clinical effectiveness. These results suggest that combining stage-structured dialogue with learned strategy selection is a promising approach for AI counseling, though clinical effectiveness, safety, and real-world utility require further human evaluation.

Related papers

• PSY-STEP: Structuring Therapeutic Targets and Action Sequences for Proactive Counseling Dialogue Systems [32.922368484671196]
  We introduce STEP, a dataset that models CBT counseling by explicitly reflecting automatic thoughts alongside dynamic, action-level counseling sequences.<n>Using this dataset, we train STEPPER, a counseling agent that proactively elicits automatic thoughts and executes cognitively grounded interventions.<n>To further enhance both decision accuracy and empathic responsiveness, we refine STEPPER through preference learning based on simulated, synthesized counseling sessions.
  arXiv  Detail & Related papers  (2026-04-06T05:47:47Z)
• A Principle-Driven Adaptive Policy for Group Cognitive Stimulation Dialogue for Elderly with Cognitive Impairment [46.48467561674335]
  We propose a principle-driven adaptive policy actualized through a Group Cognitive Stimulation Dialogue system.<n>We first construct a dataset with over 500 hours of real-world CST conversations and 10,000+ simulated dialogues generated via our Principle-Guided Scenario Simulation strategy.<n>Our GCSD system then integrates four core modules to overcome limitations: (i) a multi-speaker context controller to resolve role confusion; (ii) a cognitive stimulation-focused attention loss to instill cognitive stimulation reasoning; and (iv) a multi-dimensional reward strategy to enhance response value.
  arXiv  Detail & Related papers  (2026-03-01T15:43:21Z)
• TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling [53.46927050949822]
  We introduce TheraMind, a strategic and adaptive agent for longitudinal psychological counseling.<n>The cornerstone of TheraMind is a novel dual-loop architecture that decouples the counseling process into an Intra-Session Loop and a Cross-Session Loop.<n>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.
  arXiv  Detail & Related papers  (2025-10-29T17:54:20Z)
• Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models [72.36715571932696]
  Narrative therapy helps individuals transform problematic life stories into empowering alternatives.<n>Current approaches lack realism in specialized psychotherapy and fail to capture therapeutic progression over time.<n>Int (Interactive Narrative Therapist) simulates expert narrative therapists by planning therapeutic stages, guiding reflection levels, and generating contextually appropriate expert-like responses.
  arXiv  Detail & Related papers  (2025-07-27T11:52:09Z)
• Ψ-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedback [51.26493826461026]
  We propose Psi-Arena, an interactive framework for comprehensive assessment and optimization of large language models (LLMs)<n>Arena features realistic arena interactions that simulate real-world counseling through multi-stage dialogues with psychologically profiled NPC clients.<n>Experiments across eight state-of-the-art LLMs show significant performance variations in different real-world scenarios and evaluation perspectives.
  arXiv  Detail & Related papers  (2025-05-06T08:22:51Z)
• TRUST: An LLM-Based Dialogue System for Trauma Understanding and Structured Assessments [8.618945530676614]
  This study aims to bridge the gap in mental healthcare accessibility by developing an LLM-powered dialogue system that replicates clinician behavior.<n>We introduce TRUST, a framework of cooperative LLM modules capable of conducting formal diagnostic interviews and assessments for PTSD.<n>We develop a patient simulation approach based on real-life interview transcripts to replace time-consuming and costly manual testing by clinicians.
  arXiv  Detail & Related papers  (2025-04-30T17:58:06Z)
• Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues [75.16593367473259]
  Cognitive Restructuring (CR) is a psychotherapeutic process aimed at identifying and restructuring an individual's negative thoughts.<n>Existing efforts implement CR via simple text rewriting, fixed-pattern dialogues, or a one-shot CR workflow.<n>We propose CRDial, a novel framework for CR, which creates multi-turn dialogues with specifically designed identification and restructuring stages.
  arXiv  Detail & Related papers  (2025-04-24T04:22:00Z)
• Script-Based Dialog Policy Planning for LLM-Powered Conversational Agents: A Basic Architecture for an "AI Therapist" [0.0]
  Large Language Model (LLM)-Powered Conversational Agents have the potential to provide users with scaled behavioral healthcare support.<n>We introduce a novel paradigm for dialog policy planning in conversational agents enabling them to act according to an expert-written "script"<n>We implement two variants of Script-Based Dialog Policy Planning using different prompting techniques and synthesize a total of 100 conversations with LLM-simulated patients.
  arXiv  Detail & Related papers  (2024-12-13T12:12:47Z)
• CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy [67.23830698947637]
  We propose a new benchmark, CBT-BENCH, for the systematic evaluation of cognitive behavioral therapy (CBT) assistance.<n>We include three levels of tasks in CBT-BENCH: I: Basic CBT knowledge acquisition, with the task of multiple-choice questions; II: Cognitive model understanding, with the tasks of cognitive distortion classification, primary core belief classification, and fine-grained core belief classification; III: Therapeutic response generation, with the task of generating responses to patient speech in CBT therapy sessions.<n> Experimental results indicate that while LLMs perform well in reciting CBT knowledge, they fall short in complex real-world scenarios
  arXiv  Detail & Related papers  (2024-10-17T04:52:57Z)
• Therapy as an NLP Task: Psychologists' Comparison of LLMs and Human Peers in CBT [6.932239020477335]
  Large language models (LLMs) are being used as adhoc therapists.<n>We compare the session-level behaviors of human counselors with those of an LLM prompted by a team of peer counselors to deliver single-session Cognitive Behavioral Therapy.
  arXiv  Detail & Related papers  (2024-09-03T19:19:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.