Skip to content
conftrace_
2026 EMNLP EMNLP 2026

PSY-STEP: From Surface Problems to Underlying Beliefs through Structured Therapeutic Targets and Action Sequences

AbstractCognitive Behavioral Therapy (CBT) aims to identify and restructure automatic negative thoughts pertaining to involuntary interpretations of events, yet existing counseling agents struggle to identify and address them in dialogue settings. To bridge this gap, we introduce Step, a dataset that models CBT counseling by explicitly reflecting automatic thoughts alongside dynamic, action-level counseling sequences. Using this dataset, we train Stepper, a counseling agent that proactively elicits automatic thoughts and executes cognitively grounded interventions. To further enhance both decision accuracy and empathic responsiveness, we refine Stepper through preference learning based on simulated, synthesized counseling sessions. Extensive CBT-aligned evaluations show that Stepper delivers more clinically grounded, coherent, and personalized counseling compared to other strong baseline models, and achieves higher counselor competence without inducing emotional disruption.

More from EMNLP 2026

All EMNLP 2026 papers →