ISSN 1671-3710
CN 11-4766/R
主办:中国科学院心理研究所
出版:科学出版社

• •    

基于大模型的智能体在大学生心理咨询中的应用

郭静, 王沛, 刘荷, 王雅楠, 马胤哲, 陆锦标, 林秋吟, 陈路晰, 郭可, 陈锦瑶, 何欣   

  1. 中国人民大学人口与发展研究中心, 北京 100872 中国
    中国人民大学国家治理大数据和人工智能创新平台健康与医改政策子实验室, 北京 100872 中国
    中国人民大学人口与健康学院, 北京 100872 中国
    北京理工大学计算机学院, 北京 100871 中国
    北京理工大学网络空间安全学院, 北京 100871 中国
    冶金自动化研究设计院, 北京 100871 中国
    中国人民大学高瓴人工智能学院, 北京 100872 中国
    中国人民大学新闻学院, 北京 100872 中国
    中国人民大学哲学院, 北京 100872 中国
  • 收稿日期:2025-05-15 修回日期:2025-12-23 接受日期:2025-12-31
  • 基金资助:
    中国人民大学科学研究基金项目(25XNT005)

The Application of Large Language Model-based Intelligent Agents in College Students' Psychological Counseling

  1. , 100872, China
    , 100871, China
  • Received:2025-05-15 Revised:2025-12-23 Accepted:2025-12-31
  • Supported by:
    The Scientific Research Fund Project of Renmin University of China(25XNT005)

摘要: 大学生群体面临的心理健康挑战日趋复杂,而传统高校心理咨询模式存在一定局限。为此,本研究创新性地提出一种融合心理学与人工智能的技术框架:通过将心理咨询垂域知识与数据融入基座大模型,构建由测评师、咨询师、督导师三类心理咨询智能体与大学生智能体共同组成的“测评-咨询-督导”多智能体协作系统。系统采用“内循环训练-外循环服务”双循环模式,在“内循环训练”阶段,测评师、咨询师智能体与大学生智能体通过虚拟场景交互模拟真实咨询流程,并利用督导师智能体的反馈优化服务策略,积累个性化咨询档案与多流派干预经验;在“外循环服务”阶段,心理咨询智能体基于“内循环训练”成果,为真实来访大学生提供专业化、精准化的心理测评与干预服务。系统有望成为大学生心理咨询的有效辅助工具,助力高校心理健康服务体系实现智能化升级。

关键词: 智能体, 大模型, 心理咨询, 大学生

Abstract: The mental health challenges faced by college students are becoming increasingly complex, while the traditional college psychological counseling model has certain limitations. This study presents a novel technical framework that integrates psychology and artificial intelligence: by incorporating psychological counseling domain knowledge and data into the base model, a multi-agent collaborative system composed of three types of psychological counseling intelligent agents (evaluator, counselor, supervisor) and the college student intelligent agent is constructed. The system adopts a "double-loop" mode of "internal loop training - external loop service". In the "internal loop training" stage, the evaluator, counselor intelligent agents and the college student intelligent agent simulate the real counseling process through virtual scene interaction, and use the feedback from the supervisor intelligent agent to optimize the service strategy, accumulate personalized counseling files and multi-school intervention experience; in the "external loop service" stage, the psychological counseling intelligent agents provide professional and precise psychological assessment and intervention services for real college students based on the results of "internal loop training". The system is expected to become an effective auxiliary tool for college student psychological counseling and help the college mental health service system achieve intelligent upgrading.

Key words: intelligent agents, large language models, psychological counseling, college students