Educational-Psychological Dialogue Robot Based on Multi-Agent Collaboration
Project Overview
The document explores the innovative use of generative AI in education through the development of an intelligent dialogue system aimed at both educational and psychological counseling. This system employs multiple AI agents and utilizes large language models (LLMs) combined with retrieval-enhanced techniques to effectively respond to educational inquiries and address users' emotional needs. By integrating these advanced technologies, the system not only enhances the accuracy of educational knowledge but also offers psychological support, resulting in significant performance improvements over traditional models. The findings indicate that the system delivers comprehensive, safe, and professional services, marking a notable advancement in the application of AI in educational settings. Overall, the integration of generative AI fosters a more supportive and effective learning environment, demonstrating its potential to transform educational practices and enhance student well-being.
Key Applications
Intelligent dialogue system combining educational and psychological counseling functions
Context: Used in education and psychological counseling for students and users in need of emotional support
Implementation: Developed a multi-agent system consisting of a security detection agent, intent identification agent, educational LLM agent, and psychological LLM agent to provide accurate responses and support.
Outcomes: Demonstrated improved accuracy and user experience in educational support and psychological counseling, outperforming existing models on various subjects.
Challenges: Existing models often lack domain integration, accuracy, and professionalism when handling complex queries.
Implementation Barriers
Technical barrier
Existing dialogue systems are often limited to a single domain and lack the ability to address both educational and psychological issues effectively.
Proposed Solutions: Develop a multi-agent collaborative system that integrates both educational and psychological functionalities.
Data barrier
Insufficient availability of high-quality training data for comprehensive educational and psychological counseling.
Proposed Solutions: Utilize retrieval enhancement techniques to incorporate external knowledge bases and manually generate relevant conversation data.
Project Team
Shiwen Ni
Researcher
Min Yang
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Shiwen Ni, Min Yang
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai