Investigating AI in Peer Support via Multi-Module System-Driven Embodied Conversational Agents

2025-11-27

AI Summary

Contemporary conversational agents for peer mental health support suffer from rigid input handling, scripted responses, and insufficient emotional sensitivity—limiting their clinical applicability. To address these limitations, this paper proposes an embodied conversational agent grounded in large language models (LLMs), which innovatively integrates the cognitive behavioral therapy (CBT) framework with a multi-module collaborative architecture. This design enables task decomposition, embodied user modeling, and context-aware response generation—thereby enhancing response flexibility, situational understanding, and empathic capacity. A user study with ten participants demonstrated significant improvements across three key dimensions: response quality, workflow integration, and emotional resonance. The system’s performance validates its effectiveness in delivering adaptive, context-sensitive, and empathetic support. This work contributes both a theoretically grounded framework and an implementable methodology for developing trustworthy, personalized AI systems for psychological support.

Technology Category

• Intelligent Robots: Embodied AI
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Intelligent User Interfaces

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Young people's mental well-being is a global concern, with peer support playing a key role in daily emotional regulation. Conversational agents are increasingly viewed as promising tools for delivering accessible, personalised peer support, particularly where professional counselling is limited. However, existing systems often suffer from rigid input formats, scripted responses, and limited emotional sensitivity. The emergence of large language models introduces new possibilities for generating flexible, context-aware, and empathetic responses. To explore how individuals with psychological training perceive such systems in peer support contexts, we developed an LLM-based multi-module system to drive embodied conversational agents informed by Cognitive Behavioral Therapy (CBT). In a user study (N=10), we qualitatively examined participants' perceptions, focusing on trust, response quality, workflow integration, and design opportunities for future mental well-being support systems.

Problem

• Develops an LLM-based multi-module system for embodied conversational agents
• Explores AI-driven peer support for youth mental well-being using CBT principles
• Addresses limitations of rigid, scripted responses in existing support systems

Innovation

• LLM-based multi-module system for embodied conversational agents
• Cognitive Behavioral Therapy (CBT) informed approach for peer support
• Flexible, context-aware, and empathetic response generation