A counselor-inspired agent framework for AI counselors to enhance client engagement

Current AI counseling systems struggle with maintaining effective long-term client engagement. Through formative research with professional counselors and AI counseling practices, alongside a systematic literature review, we identified five key design considerations that bridge human counseling expertise with AI capabilities. Based on these insights, we propose CA+, a Counselor-Inspired Agent framework for AI counselors to enhance client engagement 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, establishing a foundational framework for LLM systems that demand reasoning, memory, empathy, and sustained multi-turn interactions in human-centered applications.