ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance

• URL: http://arxiv.org/abs/2608.04524v1
• Date: Wed, 05 Aug 2026 06:56:58 GMT
• Title: ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance
• Abstract summary: We introduce ODRA, a novel framework for synthesizing therapy dialogues through a Chain-of-Thought (CoT) strategy.<n>ODRA significantly outperforms existing methods across therapeutic skills, CBT alignment, and patient behavioral fidelity.
• Score: 40.60920010387361
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Synthetic generation of Cognitive Behavioral Therapy (CBT) sessions is challenged by two competing demands: adhering to strict therapeutic structure while modeling the resistant, unpredictable behavior of real patients. Existing script-based methods fail to capture dynamic therapeutic interactions, while multi-agent approaches struggle to adhere to CBT's sequential structure; both suffer from sycophancy, producing overly compliant patients that misrepresent real clinical settings. In this work we introduce ODRA, a novel framework for synthesizing therapy dialogues through a Chain-of-Thought (CoT) strategy grounded in foundational CBT guidelines (Beck, 2020). ODRA further incorporates a resistance orchestrator to solve patient sycophancy, which employs steering techniques to elicit behaviors aligned with their resistance level. Automated and expert evaluations show that ODRA significantly outperforms existing methods across therapeutic skills, CBT alignment, and patient behavioral fidelity, with licensed psychologists preferring ODRA sessions across 12 of 13 clinical metrics. Furthermore, models fine-tuned on our dataset demonstrate superior therapeutic performance against both cooperative and resistant patients, validating that explicit resistance modeling in synthetic training data directly translates to downstream clinical robustness.

Related papers

• Toward Accessible Psychotherapy Training Using AI-Driven Interactive Patient Avatars [0.45671221781968324]
  Training psychotherapists in Acceptance and Commitment Therapy (ACT) requires repeated practice with meaningful feedback.<n>We introduce a system designed to support ACT-oriented psychotherapy training through spoken dialogue with an embodied virtual patient.
  arXiv  Detail & Related papers  (2026-06-16T11:02:00Z)
• Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model [57.78184285979881]
  We introduce SepsisAgent, a world model-augmented LLM agent for sepsis treatment recommendation.<n>SepsisAgent uses a learned Clinical World Model to simulate patient responses under candidate fluid--vasopressor interventions.
  arXiv  Detail & Related papers  (2026-05-14T11:50:00Z)
• From Synthesis to Clinical Assistance: A Strategy-Aware Agent Framework for Autism Intervention based on Real Clinical Dataset [5.158237631119026]
  textscASDAgent is a strategy-aware framework designed to unify high-fidelity intervention dialogue synthesis and clinical decision support.<n>In real autism intervention, textscASDAgent achieves nearly 80% strategic consistency with human experts.
  arXiv  Detail & Related papers  (2026-04-09T03:28:46Z)
• CCD-CBT: Multi-Agent Therapeutic Interaction for CBT Guided by Cognitive Conceptualization Diagram [7.766423559393797]
  We introduce CCD-CBT, a multi-agent framework that shifts CBT simulation along two axes.<n>We show that models fine-tuned on CCDCHAT outperform strong baselines in both counseling fidelity and positive-affect enhancement.
  arXiv  Detail & Related papers  (2026-04-08T00:58:58Z)
• 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)
• XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being [31.750822070511138]
  We present textbfXInsight, a counseling-inspired multi-agent framework.<n>XInsight orchestrates specialized agents under a unified textitReason-Intervene-Reflect cycle.<n>Recording agent transforms open-ended web dialogues into standardized psychological artifacts.
  arXiv  Detail & Related papers  (2026-01-21T11:26:24Z)
• 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)
• MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance [33.081670638470165]
  We propose a multimodal approach that incorporates nonverbal cues, which allows the AI therapist to better align its responses with the client's negative emotional state.<n>Specifically, we introduce a new synthetic dataset, Mirror, which is a novel synthetic dataset that pairs each client's statements with corresponding facial images.<n>Our results demonstrate that Mirror significantly enhances the AI therapist's ability to handle resistance, which outperforms existing text-based CBT approaches.
  arXiv  Detail & Related papers  (2025-04-16T08:44:26Z)
• COMPASS: Computational Mapping of Patient-Therapist Alliance Strategies with Language Modeling [14.04866656172336]
  The therapeutic working alliance is a critical predictor of psychotherapy success.<n>In this paper, we present a novel framework to infer the therapeutic working alliance from the natural language used in psychotherapy sessions.
  arXiv  Detail & Related papers  (2024-02-22T16:56:44Z)
• Safe and Interpretable Estimation of Optimal Treatment Regimes [54.257304443780434]
  We operationalize a safe and interpretable framework to identify optimal treatment regimes. Our findings support personalized treatment strategies based on a patient's medical history and pharmacological features.
  arXiv  Detail & Related papers  (2023-10-23T19:59:10Z)
• TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network [54.332862955411656]
  Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically matching patients with clinical trials. We introduce a dynamic tree-based memory network model named TREEMENT to provide accurate and interpretable patient trial matching.
  arXiv  Detail & Related papers  (2023-07-19T12:35:09Z)
• Automated Fidelity Assessment for Strategy Training in Inpatient Rehabilitation using Natural Language Processing [53.096237570992294]
  Strategy training is a rehabilitation approach that teaches skills to reduce disability among those with cognitive impairments following a stroke. Standardized fidelity assessment is used to measure adherence to treatment principles. We developed a rule-based NLP algorithm, a long-short term memory (LSTM) model, and a bidirectional encoder representation from transformers (BERT) model for this task.
  arXiv  Detail & Related papers  (2022-09-14T15:33:30Z)

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.