PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism AI Psychological Counselor

2026-01-05

arXiv.org

AI Summary

This work proposes a longitudinal psychotherapy benchmark designed to train and systematically evaluate AI counselors with high clinical realism, supporting multiple therapeutic modalities and treatment sessions. The benchmark encompasses five major therapeutic approaches across 6–10 sessions per case, emphasizing critical capabilities such as memory continuity, dynamic goal tracking, and cross-session planning. Integrating multi-modal, multi-stage, and multi-session characteristics, it leverages expert-annotated taxonomies of 677 meta-skills and 4,577 atomic skills to generate over 2,000 diverse client profiles. The framework includes 18 evaluation metrics—spanning both therapy-specific and general counseling competencies—to enable comprehensive assessment. Experimental validation confirms the dataset’s high quality and clinical fidelity, establishing a realistic, reinforcement learning–compatible environment for training and evaluating AI-driven psychological counseling systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

To develop a reliable AI for psychological assessment, we introduce \texttt{PsychEval}, a multi-session, multi-therapy, and highly realistic benchmark designed to address three key challenges: \textbf{1) Can we train a highly realistic AI counselor?} Realistic counseling is a longitudinal task requiring sustained memory and dynamic goal tracking. We propose a multi-session benchmark (spanning 6-10 sessions across three distinct stages) that demands critical capabilities such as memory continuity, adaptive reasoning, and longitudinal planning. The dataset is annotated with extensive professional skills, comprising over 677 meta-skills and 4577 atomic skills. \textbf{2) How to train a multi-therapy AI counselor?} While existing models often focus on a single therapy, complex cases frequently require flexible strategies among various therapies. We construct a diverse dataset covering five therapeutic modalities (Psychodynamic, Behaviorism, CBT, Humanistic Existentialist, and Postmodernist) alongside an integrative therapy with a unified three-stage clinical framework across six core psychological topics. \textbf{3) How to systematically evaluate an AI counselor?} We establish a holistic evaluation framework with 18 therapy-specific and therapy-shared metrics across Client-Level and Counselor-Level dimensions. To support this, we also construct over 2,000 diverse client profiles. Extensive experimental analysis fully validates the superior quality and clinical fidelity of our dataset. Crucially, \texttt{PsychEval} transcends static benchmarking to serve as a high-fidelity reinforcement learning environment that enables the self-evolutionary training of clinically responsible and adaptive AI counselors.

Problem

• AI psychological counselor
• multi-session counseling
• multi-therapy integration
• realism in AI counseling
• systematic evaluation

Innovation

• multi-session counseling
• multi-therapy integration
• longitudinal AI training
• clinical evaluation framework
• reinforcement learning environment