认知回响:学习者智能体的出声思维研究  

Cognitive Echo:The Think-aloud Protocol for Simulated Student Agents

作　　者：郑隆威 贺安娜 齐长永 胡碧皓 顾小清[3] 洪道诚 Zheng Longwei;He Anna;Qi Changyong;Hu Bihao;Gu Xiaoqing;Hong Daocheng(School of Education,City University of Macao,Macao 999078,China;School of Computer Science and Technology,East China Normal University,Shanghai 200062,China;Department of Education Information and Technology,East China Normal University,Shanghai 200062,China)

机构地区：[1]澳门城市大学教育学院,中国澳门999078 [2]华东师范大学计算机科学与技术学院,上海200062 [3]华东师范大学上海数字化教育装备工程技术研究中心,上海200062

出　　处：《华东师范大学学报(教育科学版)》2025年第5期30-43,共14页Journal of East China Normal University:Educational Sciences

基　　金：国家社会科学基金教育学一般项目“生成式教学制品中教师数字素养的多重表达与评价研究”(BCA240054)。

摘　　要：该研究将出声思维法与大语言模型相结合,提出“认知回响”这一新方法,补充了传统的同步出声思维法,以解决数据采集干扰思维过程的局限性。研究设计了一种能够模拟不同学生认知过程的角色智能体,并基于学习情景的再现、学习经历的重构及上传,构建了一个智能体训练框架。与传统的提示工程方法相比,该框架通过真实学习记录生成虚拟学习经历,使不同智能体能够更加准确地模拟各类学生的认知反应。研究通过对少量数据的微调训练,验证了学生智能体在认知模拟方面的潜力。结果表明,各类学生智能体能够从存量学习数据中自主获取学习经验,并基于此提供有效思维报告。这一方法可应用基于模拟的决策和培训中,这将有助于降低教育创新的成本和风险。This study proposes a trainable role-played agent capable of simulating students’cognition by integ-rating the think-aloud protocol with large language models.The research develops an agent training framework based on the reconstruction and uploading of learning experiences and the reproduction of learning scenarios.Compared to traditional prompt-engineering approaches,this framework generates simulated learning experiences from authentic learning records,allowing the agent to more accurately simulate students’cognition.Through fine-tuning with lim-ited data,the effectiveness of the agent in cognitive simulation is demonstrated.A new method,“Cognitive Echo,”is introduced to supplement the traditional synchronous think-aloud method.This approach reduces interference in cog-nitive data collection.The results indicate that the agent can acquire learning experiences from existing data without the need for complex domain modeling.This makes the agent applicable to various fields such as educational de-cision-making simulation and teacher training.As a result,it helps reduce the costs and risks associated with educa-tional innovation.

关 键 词：出声思维 认知回响 角色智能体 多智能体 大语言模型 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]