Reshaping self-regulated learning in K-12 AI courses: a learning support framework based on LLM agents

Gao Xin; Huang Jun; Wang Li; Li Na; Ma Jimei

doi:10.11959/j.issn.2096-6652.ZNKX26065

您当前的位置：

首页 >

文章列表页 >

Reshaping self-regulated learning in K-12 AI courses: a learning support framework based on LLM agents

Papers and Reports | 更新时间：2026-07-29

- Reshaping self-regulated learning in K-12 AI courses: a learning support framework based on LLM agents
- Chinese Journal of Intelligent Science and Technology Vol. 8, Issue 2, Pages: 264-277(2026)
- 作者机构：
  
  1.天津市第二中学，天津 300140
  2.澳门科技大学创新工程学院工程科学系，澳门 999078
  3.中国科学院自动化研究所多模态人工智能系统全国重点实验室，北京 100190
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-6652.ZNKX26065
  CLC： G482
- Received：22 April 2026，
  
  Revised：2026-07-11，
  
  Accepted：17 July 2026，
  
  Online First：27 July 2026，
  
  Published：15 June 2026
- 稿件说明：
移动端阅览
高欣,黄峻,王丽等.K-12 AI课程的自我调节学习重塑：基于LLM智能体的学习辅助框架[J].智能科学与技术学报,2026,08(02):264-277.

Gao Xin,Huang Jun,Wang Li,et al.Reshaping self-regulated learning in K-12 AI courses: a learning support framework based on LLM agents[J].Chinese Journal of Intelligent Science and Technology,2026,08(02):264-277.
高欣,黄峻,王丽等.K-12 AI课程的自我调节学习重塑：基于LLM智能体的学习辅助框架[J].智能科学与技术学报,2026,08(02):264-277. DOI： 10.11959/j.issn.2096-6652.ZNKX26065.

Gao Xin,Huang Jun,Wang Li,et al.Reshaping self-regulated learning in K-12 AI courses: a learning support framework based on LLM agents[J].Chinese Journal of Intelligent Science and Technology,2026,08(02):264-277. DOI： 10.11959/j.issn.2096-6652.ZNKX26065.

摘要

当前K-12人工智能（AI）课程正逐步向常态化项目式教学深化，但在教学实践中，普遍存在学生主体目标设定模糊、复杂工程探究过程难以感知，以及高阶反思缺失等瓶颈。同时，大型语言模型（LLM）在基础教育中的常态应用多倾向于结果导向的知识直接输出，在一定程度上消解了学生的自主试错与思维建构空间，制约了其自我调节学习（SRL）能力的发展。作为推动复杂工程问题解决的核心元认知要素，自我调节学习能力的良性发展直接决定了学生在不确定技术情境下的策略迁移与高阶思维成效。为此，依托平行教学实验室基础设施，提出一种基于LLM智能体的平行自我调节学习支持框架。该框架将复杂项目解构为良构的任务节点，并在规划、执行与反思的SRL循环体系中部署多角色智能体。在运行机制上，利用人工系统沉淀工程化探究全过程的过程性日志；通过计算实验推演学生的认知偏差与策略偏移；最终基于平行执行机制将诊断结果转化为启发式支架与教师的调控实据，实现外部技术支持向内在元认知监控的平滑转化。最后，结合天津市第二中学智慧出行实验室及校本AI+课程体系开展设计型案例分析，论证了该框架在多类工程实践项目中的落地路径，为过程数据驱动的基础教育智能教学实证研究提供了新视角与系统化范式。

Abstract

Current K-12 artificial intelligence (AI) education is progressively shifting toward regularized

project-based instruction. However

pedagogical practices still suffer from obscured learning paths

insufficient perception of cognitive processes

and a lack of high-order reflection. Meanwhile

the routine use of large language models (LLM) in basic education often tends to be outcome-oriented

providing direct knowledge outputs. To some extent

this may reduce students' opportunities for autonomous trial and error as well as their space for cognitive construction

thereby constraining the development of their self-regulated learning (SRL) abilities. As a core metacognitive factor that supports the solving of complex engineering problems

the healthy development of SRL abilities directly determines students' capacity for strategy transfer and higher-order thinking in uncertain technological contexts. To address these challenges

an LLM agent-driven support framework for self-regulated learning was proposed embedded within the infrastructure of a parallel teaching laboratory. Synthesizing the planning-performance-reflection cycle of SRL

the framework operationalized complex AI projects into structured

node-based task spaces monitored by multi-role agents. Under the artificial systems

computational experiments

and parallel execution (ACP) approach

the framework leveraged artificial systems to capture multimodal process logs

conducted computational experiments to infer students' strategic deviations and cognitive obstacles

and utilized parallel execution to deliver heuristic prompts and teacher-facing evidence. Finally

a design-oriented case study was presented grounded in the Intelligent Mobility AI Laboratory and the school-based "AI+" curriculum at Tianjin No. 2 High School

illustrating the integration paths across various experimental projects and establishing a systemic foundation for subsequent empirical studies driven by fine-grained process data.

关键词

Keywords

references

Dewey J. Experience and education[J]. The Educational Forum, 1986, 50(3): 241-252.

Wooster J S, Papert S. Mindstorms: children, computers, and powerful ideas[J]. The English Journal, 1982, 71(8): 60.

Ambrose S A. How Learning Works: Seven Research-Based Principles for Smart Teaching[M]. San Francisco: Jossey-Bass, 2010.

Long D R, Magerko B. What is AI literacy? competencies and design considerations[C]//Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. New York: ACM Press, 2020: 1-16.

Touretzky D, Gardner-McCune C, Martin F, et al. Envisioning AI for K-12: what should every child know about AI?[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 9795-9799.

Chiu T K F, Meng H, Chai C S, et al. Creation and evaluation of a pretertiary artificial intelligence (AI) curriculum[J]. IEEE Transactions on Education, 2022, 65(1): 30-39.

Yim I H Y, Su J H. Artificial intelligence (AI) learning tools in K-12 education: a scoping review[J]. Journal of Computers in Education, 2024: 93-131.

Zhang T Y, Lai Y C, Yu P L H. Generative artificial intelligence in K-12 education: a systematic review[J]. Research and Practice in Technology Enhanced Learning, 2025, 21: 34.

Zimmerman B J. Attaining self-regulation: a social cognitive perspective[M]. New York: Academic Press, 2000: 13-39.

Pintrich P R. The role of goal orientation in self-regulated learning[M].Amsterdam: Elsevier, 2000: 451-502.

Winne P H, Perry N E. Measuring self-regulated learning[M]. Amsterdam: Elsevier, 2000: 531-566.

Panadero E. A review of self-regulated learning: six models and four directions for research[J]. Frontiers in Psychology, 2017, 8: 422.

Broadbent J, Poon W L. Self-regulated learning strategies & academic achievement in online higher education learning environments: a systematic review[J]. The Internet and Higher Education, 2015, 27: 1-13.

Kasneci E, Sessler K, Küchemann S, et al. ChatGPT for good? On opportunities and challenges of large language models for education[J]. Learning and Individual Differences, 2023, 103: 102274.

Hwang G J, Xie H R, Wah B W, et al. Vision, challenges, roles and research issues of Artificial Intelligence in Education[J]. Computers and Education: Artificial Intelligence, 2020, 1: 100001.

Zhai X M. ChatGPT user experience: implications for education[J]. SSRN Electronic Journal, 2022: 1-10.

Ge W T, Sun Y Q, Wang Z Y, et al. SRLAgent: enhancing self-regulated learning skills through gamification and LLM assistance[PP]. V1. (2025-06-11)[2026-04-22]. arXiv: arXiv.2506.09968.

Vygotsky L S. Mind in Society: Development of Higher Psychological Processes[M]. Cambridge: Harvard University Press, 1980.

Wood D, Bruner J S, Ross G. The role of tutoring in problem SOLVING * [J ] . Journal of Child Psychology and Psychiatry, 1976, 17(2): 89-100.

Cao X M, Xu S T, Chen X Y, et al. Leveraging generative AI agent to promote teaching reflection in a K-12 AI course: effects on teachers' reflection self-efficacy, instructional design, and reflective thinking[J]. IEEE Transactions on Learning Technologies, 2026, 19: 127-140.

Bauer E, Greiff S, Graesser A C, et al. Looking beyond the hype: understanding the effects of AI on learning[J]. Educational Psychology Review, 2025, 37(2): 45.

Boulhrir T, Hamash M. Unpacking artificial intelligence in elementary education: a comprehensive thematic analysis systematic review[J]. Computers and Education: Artificial Intelligence, 2025, 9: 100442.

Chu Z D, Wang S, Xie J, et al. LLM agents for education: advances and applications[PP]. V2. (2026-02-04)[2026-04-22]. arXiv: arXiv.2503.11733.

Wang T F, Zhan Y, Lian J X, et al. LLM-powered multi-agent framework for goal-oriented learning in intelligent tutoring system[C]//Proceedings of the ACM on Web Conference 2025. New York: ACM Press, 2025: 510-519.

Xing W L, Nixon N, Crossley S, et al. The use of large language models in education[J]. International Journal of Artificial Intelligence in Education, 2025, 35(2): 439-443.

Wang S, Xu T L, Li H, et al. Large language models for education: a survey and outlook[J]. IEEE Signal Processing Magazine, 2025, 42(6): 51-63.

Raihan N, Siddiq M L, Santos J C S, et al. Large language models in computer science education: a systematic literature review[C]//Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 1. New York: ACM Press, 2025: 938-944.

Lan M, Zhou X F. A qualitative systematic review on AI empowered self-regulated learning in higher education[J]. NPJ Science of Learning, 2025, 10: 21.

Mooij S D, Lämsä J, Lim L, et al. A systematic review of self-regulated learning through integration of multimodal data and artificial intelligence[J]. Educational Psychology Review, 2025, 37(2): 54.

王飞跃. 平行系统方法与复杂系统的管理和控制[J]. 控制与决策, 2004, 19(5): 485-489, 514.

Wang F Y. Parallel system methods for management and control of complex systems[J]. Control and Decision, 2004, 19(5): 485-489, 514.

Wang F Y, Wang X, Li L X, et al. Steps toward parallel intelligence[J]. CAA Journal of Automatica Sinica, 2016, 3(4): 345-348.

高欣, 林飞, 傅君, 等. 平行教学实验室: 赋能K-12教育的新AI基础设施[J]. 智能科学与技术学报, 2026, 8(1): 94-104.

Gao X, Lin F, Fu J, et al. Parallel teaching laboratories: a new AI infrastructure empowering K-12 education[J]. Chinese Journal of Intelligent Science and Technology, 2026, 8(1): 94-104.

Thomas J W. A review of research on project-based learning[R]. 2000.

Bell S. Project-based learning for the 21st century: skills for the future[J]. The Clearing House: A Journal of Educational Strategies, Issues and Ideas, 2010, 83(2): 39-43.

Kokotsaki D, Menzies V, Wiggins A. Project-based learning: a review of the literature[J]. Improving Schools, 2016, 19(3): 267-277.

Grover S, Pea R. Computational thinking in K-12: a review of the state of the field[J]. Educational Researcher, 2013, 42(1): 38-43.

Brennan K, Resnick M. New frameworks for studying and assessing the development of computational thinking[C]//Proceedings of the 2012 Annual Meeting of the American Educational Research Association. Vancouver: American Educational Research Association, 2012:1- 25.

Lye S Y, Koh J H L. Review on teaching and learning of computational thinking through programming: What is next for K-12?[J]. Computers in Human Behavior, 2014, 41: 51-61.

Shute V J, Sun C, Asbell-Clarke J. Demystifying computational thinking[J]. Educational Research Review, 2017, 22: 142-158.

Robins A, Rountree J, Rountree N. Learning and teaching programming: a review and discussion[J]. Computer Science Education, 2003, 13(2): 137-172.

Lister R, Adams E S, Fitzgerald S, et al. A multi-national study of reading and tracing skills in novice programmers[J]. ACM SIGCSE Bulletin, 2004, 36(4): 119-150.

Sweller J. Cognitive load during problem solving: effects on learning[J]. Cognitive Science, 1988, 12(2): 257-285.

Sweller J, van Merrienboer J J G, Paas F G W C. Cognitive architecture and instructional design[J]. Educational Psychology Review, 1998, 10(3): 251-296.

Siemens G. Learning analytics: the emergence of a discipline[J]. American Behavioral Scientist, 2013, 57(10): 1380-1400.

Gašević D, Dawson S, Siemens G. Let's not forget: Learning analytics are about learning[J]. TechTrends, 2015, 59(1): 64-71.

Wise A F, Shaffer D W. Why theory matters more than ever in the age of big data[J]. Journal of Learning Analytics, 2015, 2(2): 5-13.

Kapur M. Productive failure[J]. Cognition and Instruction, 2008, 26(3): 379-424.

Chi M T H, Wylie R. The ICAP framework: linking cognitive engagement to active learning outcomes[J]. Educational Psychologist, 2014, 49(4): 219-243.

Woolf B P. Building Intelligent Interactive Tutors: Student-Centered Strategies for Revolutionizing E-Learning[M]. Burlington: Morgan Kaufmann Publishers, 2009.

Vanlehn K. The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems[J]. Educational Psychologist, 2011, 46(4): 197-221.

Yao S, Zhao J, Yu D, et al. ReAct: synergizing reasoning and acting in language models[PP]. V3. (2023-03-10) [2026-04-22]. arXiv: arXiv.2210.03629 .

Park J S, O'Brien J, Cai C J, et al. Generative agents: interactive simulacra of human behavior[C]//Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. New York: ACM Press, 2023: 1-22.

Wu Q, Bansal G, Zhang J, et al. Autogen: enabling next-gen LLM applicationsvia multi-agent conversations[PP]. V2. (2023-10-03) [2026-04-22]. arXiv:arXiv:2308.08155.

Liu P F, Yuan W Z, Fu J L, et al. Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing[J]. ACM Computing Surveys, 2023, 55(9): 1-35.

黄峻, 林飞, 杨静, 等. 生成式AI的大模型提示工程: 方法、现状与展望[J]. 智能科学与技术学报, 2024, 6(2): 115-133.

Huang J, Lin F, Yang J, et al. From prompt engineering to generative artificial intelligence for large models: the state of the art and perspective[J]. Chinese Journal of Intelligent Science and Technology, 2024, 6(2): 115-133.

Lewis P, Perez E, Piktus A, et al. Retrieval-augmented generation for knowledge-intensive NLP tasks[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. New York: ACM Press, 2020: 9459-9474.

Collins A, Brown J S, Newman S E. Cognitive apprenticeship: teaching the Crafts of reading, writing, and mathematics[C]//Knowing, Learning, and Instruction: Essays in Honor of Robert Glaser. London: Routledge, 2018: 453-494.

Puntambekar S, Hubscher R. Tools for scaffolding students in a complex learning environment: what have we gained and what have we missed?[J]. Educational Psychologist, 2005, 40(1): 1-12.

教育部. 义务教育信息科技课程标准(2022年版)[M]. 北京: 北京师范大学出版社, 2022.

Ministry of Education of the People's Republic of China. Compulsory education information technology curriculum standards (2022 edition)[M]. Beijing: Beijing Normal University Press, 2022.

教育部. 普通高中信息技术课程标准(2017年版2020年修订)[M]. 北京: 人民教育出版社, 2020.

Ministry of Education of the People's Republic of China. General senior high school information technology curriculum standards (2017 edition, revised in 2020)[M]. Beijing: People's Education Press, 2020.

国务院. 新一代人工智能发展规划[Z]. 2017.

State Council of the People's Republic of China. New generation artificial intelligence development plan[Z]. 2017.

教育部. 教育部2022年工作要点[Z]. 2022.

Ministry of Education of the People's Republic of China. Key tasks of the Ministry of Education in 2022[Z]. 2022.

祝智庭, 胡姣. 教育数字化转型的本质探析与研究展望[J]. 中国电化教育, 2022(4): 9.

Zhu Z T, Hu J. Exploring the essence of digital transformation in education and research prospects[J]. China Educational Technology, 2022(4): 9.

黄荣怀, 高博俊, 王欢欢, 等. 基于教学过程感知的行为计算[J]. 电化教育研究, 2020, 41(6): 20-26.

Huang R H, Gao B J, Wang H H, et al. Behavioral computing based on perception of teaching process[J]. E-education Research, 2020, 41(6): 20-26.

王飞跃. 数字教师与平行教育: 关于ChatGPT之后教学变革的探讨[J]. 智能科学与技术学报, 2023, 5(4): 454-463.

Wang F Y. Digital teachers and parallel education: a paradigm shift in teaching and learning after ChatGPT[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(4): 454-463.

Amershi S, Weld D, Vorvoreanu M, et al. Guidelines for human-AI interaction[C]//Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. New York: ACM Press, 2019: 1-13.

Shneiderman B. Human-centered artificial intelligence: reliable, safe & trustworthy[J]. International Journal of Human-Computer Interaction, 2020, 36(6): 495-504.

Jobin A, Ienca M, Vayena E. The global landscape of AI ethics guidelines[J]. Nature Machine Intelligence, 2019, 1(9): 389-399.

Unesco. AI and education: guidance for policy-makers[M]. Paris: UNESCO, 2021.

Luckin R, Holmes W, Griffiths M, et al. Intelligence unleashed: an argument for AI in education[M]. London: Pearson, 2016.

Holmes W, Bialik M, Fadel C. Artificial Intelligence in education: promises and implications for teaching and learning[M]. Boston: Center for Curriculum Redesign, 2019.

Selwyn N. Should robots replace teachers : AI and the future of education[M]. Cambridge: John Wiley &Sons, 2019.

Baker R S, Martin T, Rossi L M. Educational data mining and learning analytics[M]. Hoboken: John Wiley & Sons, Inc.2016: 379-396.

Williamson B, Eynon R, Potter J. Pandemic politics, pedagogies and practices: digital technologies and distance education during the coronavirus emergency[J]. Learning, Media and Technology, 2020, 45(2): 107-114.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Parallel teaching laboratories: a new AI infrastructure empowering K-12 education

Parallel Macao field observatory: autonomous systems for global intelligent observation and emergency management

Parallel drug systems: framework and methods based on large language models and three types of humans

Digital teachers and parallel education: A paradigm shift in teaching and learning after ChatGPT

YOLO-TKD: lightweight temporal interactive signal detection model for autonomous driving

Related Author

Lin Fei

Fu Jun

Sun Jianjun

Huang Jun

Joseph Hun-Wei Lee

Ni Qinghua

Lin Fei

Tian Yonglin

Related Institution

Qingdao Academy of Intelligent Industries

Environmental Research Institute, Macau University of Science and Technology, Macao

State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences

DeSci Center of Parallel Intelligence, Óbuda University

Department of Engineering Science, Faculty of Innovation Engineering, Macau University of Science and Technology, Macau

Postal code：100079
Tel：（010）53879206 Email：cjist@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：185511 Visits Today：506

⁰