aiqbench analysis
This research addresses a critical gap in LLM applications for therapy by shifting from isolated response generation to modeling longitudinal therapeutic state evolution across multiple sessions. The proposed DMT-CBT framework integrates multimodal behavioral grounding and tool-augmented interventions to better capture the dynamic nature of real-world psychotherapy. By introducing a synthetic multi-session dataset, the work provides a necessary foundation for developing more faithful and adaptive AI counseling systems.
DMT-CBT: Longitudinal Therapeutic State Modeling for CBT Counseling
arXiv:2606.03132v1 Announce Type: new Abstract: Large language models (LLMs) have shown growing potential for Cognitive Behavioral Therapy (CBT) counseling. However, most existing approaches still formulate counseling as a local response generation problem, focusing on empathetic replies within short, text-only, or single-session interactions. We argue that this formulation fundamentally mismatches the nature of real psychotherapy. In clinical CBT, therapy is a longitudinal process in which therapists continuously infer, update, and intervene on evolving therapeutic states across sessions. Realistic CBT further involves multimodal inference and delayed cross-session intervention effects, requiring models to capture longitudinal therapeutic state evolution under partial observability. We propose DMT-CBT, a framework for Dynamic Modeling of evolving Therapeutic states in CBT counseling. DMT-CBT maintains structured therapeutic states across sessions while incorporating multimodal behavioral grounding and tool-augmented intervention to support adaptive therapeutic reasoning. Based on this framework, we construct DMTCorpus, a synthetic multi-session multimodal CBT counseling dataset featuring evolving therapeutic states, image-grounded client behaviors, and cross-session intervention continuity. Experimental results show that DMT-CBT improves counseling fidelity and therapeutic alliance, produces more favorable longitudinal affective trajectories, and preserves therapeutic states more faithfully than post-hoc extraction approaches.
Abstract:Large language models (LLMs) have shown growing potential for Cognitive Behavioral Therapy (CBT) counseling. However, most existing approaches still formulate counseling as a local response generation problem, focusing on empathetic replies within short, text-only, or single-session interactions. We argue that this formulation fundamentally mismatches the nature of real psychotherapy. In clinical CBT, therapy is a longitudinal process in which therapists continuously infer, update, and intervene on evolving therapeutic states across sessions. Realistic CBT further involves multimodal inference and delayed cross-session intervention effects, requiring models to capture longitudinal therapeutic state evolution under partial observability. We propose DMT-CBT, a framework for Dynamic Modeling of evolving Therapeutic states in CBT counseling. DMT-CBT maintains structured therapeutic states across sessions while incorporating multimodal behavioral grounding and tool-augmented intervention to support adaptive therapeutic reasoning. Based on this framework, we construct DMTCorpus, a synthetic multi-session multimodal CBT counseling dataset featuring evolving therapeutic states, image-grounded client behaviors, and cross-session intervention continuity. Experimental results show that DMT-CBT improves counseling fidelity and therapeutic alliance, produces more favorable longitudinal affective trajectories, and preserves therapeutic states more faithfully than post-hoc extraction approaches.
Computation and Language (cs.CL)
arXiv:2606.03132 [cs.CL]
(or arXiv:2606.03132v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.03132 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 275 words
Related coverage
Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs
arXiv · Sep 1, 2026
Steering the Compass: Aligning Dynamic Psychological Counseling Conversations with Cognitive Behavioral Therapy Strategies
arXiv · Sep 18, 2026
PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time
arXiv · Oct 6, 2026
HealthLoopQA: A Context-Aware Question Answering Benchmark for Interpreting Wearable Monitoring Data in Diabetes Care
arXiv · Sep 9, 2026