CA+: Cognition Augmented Counselor Agent Framework for Long-term Dynamic Client Engagement

TL;DR

This paper presents CA+, a Cognition Augmented Counselor Agent framework designed to address long-term engagement gaps in AI-based psychological counseling. It integrates three components—Therapy Strategies, Communication Form, and Information Management—within a recursive, hierarchically layered planning architecture to maintain context, adaptively personalize interventions, and preserve therapeutic continuity. Two studies demonstrate significant improvements in client engagement, perceived empathy, and satisfaction, with professional counselors endorsing CA+’s professionalism and adherence to counseling standards. The work advances AI-assisted mental health by providing a scalable, knowledge-rich framework that leverages cognitive theories and AI strengths to extend access to high-quality psychological support while outlining clear directions for future enhancements and safety considerations.

Abstract

Current AI counseling systems struggle with maintaining effective long-term client engagement. Through formative research with counselors and a systematic literature review, we identified five key design considerations for AI counseling interactions. Based on these insights, we propose CA+, a Cognition Augmented counselor framework enhancing contextual understanding through three components: (1) Therapy Strategies Module: Implements hierarchical Goals-Session-Action planning with bidirectional adaptation based on client feedback; (2) Communication Form Module: Orchestrates parallel guidance and empathy pathways for balanced therapeutic progress and emotional resonance; (3) Information Management: Utilizes client profile and therapeutic knowledge databases for dynamic, context-aware interventions. A three-day longitudinal study with 24 clients demonstrates CA+'s significant improvements in client engagement, perceived empathy, and overall satisfaction compared to a baseline system. Besides, two licensed counselors confirm its high professionalism. Our research demonstrates the potential for enhancing LLM engagement in psychological counseling dialogues through cognitive theory, which may inspire further innovations in computational interaction in the future.

Figures (19)

• Figure 1: PRISMA flow diagram illustrating the literature selection process.
• Figure 2: Examples of Three Layers Content in CA+ System.
• Figure 3: Examples of Case Conceptualization and Counseling Record Documentation in CA+ System.
• Figure 4: Book-style Data Generation and Retrieval. This framework illustrates the process of generating and retrieving structured data for therapeutic use, leveraging a knowledge base to enhance counseling interventions.
• Figure 5: The DG4 approach enhances therapeutic interactions through two key mechanisms: adaptive empathy that balances immediate responsiveness with long-term personality, and an ecological self-framework that integrates professional competence with personalized character traits.