From 50% to Mastery in 3 Days: A Low-Resource SOP for Localizing Graduate-Level AI Tutors via Shadow-RAG
School of Mechanics and Engineering Science, Peking University, Beijing, 100871, China(北京理工大学机械与工程科学学院);Readraft Intelligent Technology Co., Ltd., China(读raft智能科技有限公司);Graduate School of Education, Peking University, Beijing, 100871, China(北京大学教育学院);AI for Science Institute, Beijing, 100080, China(AI for Science研究院)
Deploying high-fidelity AI tutors in schools is often blocked by the Resource Curse -- the need for expensive cloud GPUs and massive data engineering. In this practitioner report, we present a replicable Standard Operating Procedure that breaks this barrier. Using a Vision-Language Model data cleaning strategy and a novel Shadow-RAG architecture, we localized a graduate-level Applied Mathematics tutor using only 3 person-days of non-expert labor and open-weights 32B models deployable on a single consumer-grade GPU. Our pilot study on a full graduate-level final exam reveals a striking emergence phenomenon: while both zero-shot baselines and standard retrieval stagnate around 50-60% accuracy across model generations, the Shadow Agent, which provides structured reasoning guidance, triggers a massive capability surge in newer 32B models, boosting performance from 74% (Naive RAG) to mastery level (90%). In contrast, older models see only modest gains (~10%). This suggests that such guidance is the key to unlocking the latent power of modern small language models. This work offers a cost-effective, scientifically grounded blueprint for ubiquitous AI education.
RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoring
College of Information Science, University of Arizona, Tucson, AZ, USA(信息科学学院,亚利桑那大学);Department of Electrical and Computer Engineering, University of Arizona, Tucson, AZ, USA(电气与计算机工程系,亚利桑那大学);Department of Systems and Industrial Engineering, University of Arizona, Tucson, AZ, USA(系统与工业工程系,亚利桑那大学);Department of Industrial Engineering, University of Sonora, Hermosillo, Mexico(工业工程系,索诺拉大学);Leonhard Center for Enhancement of Engineering Education, The Pennsylvania State University, University Park, PA, USA(工程教育增强中心,宾夕法尼亚州立大学)
Problems With Large Language Models for Learner Modelling: Why LLMs Alone Fall Short for Responsible Tutoring in K--12 Education
School of Digital Technologies(数字技术学院);Tallinn University(塔林大学);Faculty of Information Technology(信息技术学院);University of Jyväskylä(耶夫斯凯利亚大学);Department of Computer Science and Engineering(计算机科学与工程系);Gangneung-Wonju National University(江原-Wonju国立大学);Czech Technical University(捷克技术大学);University College London(伦敦大学学院);School of Modeling Simulation and Training(建模模拟与培训学院);University of Central Florida(中央佛罗里达大学)
Hey Chat, Can You Teach Me? Structuring Socratic Dialogue for Human Learning in the Wild
School of Computing and Information Systems, Singapore Management University(新加坡管理大学计算与信息系统学院);Department of Management Science and Information Systems, Rutgers Business School(罗格斯大学商学院管理科学与信息系统系)
SPL: A Socratic Playground for Learning Powered by Large Language Model
Institute for Intelligent Systems, University of Memphis(孟菲斯大学智能系统研究所);University of Memphis(孟菲斯大学);School of Computer Science, Carnegie Mellon University(卡内基梅隆大学计算机科学学院);School of Psychology, Shaanxi Normal University(陕西师范大学心理学院);School of Psychology, Central China Normal University(华中师范大学心理学院);Department of Applied Social Sciences, Hong Kong Polytechnic University(香港理工大学应用社会科学系)
The Grainger College of Engineering, Department of Civil and Environmental Engineering, University of Illinois at Urbana-Champaign, 205 N Matthews, Urbana, IL 61801(伊利诺伊大学厄巴纳-香槟分校格拉inger工程学院,土木与环境工程系)
CoderAgent: Simulating Student Behavior for Personalized Programming Learning with Large Language Models
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(人工智能研究院,合肥综合性国家科学中心)
Improving Low-Resource Knowledge Tracing Tasks by Supervised Pre-training and Importance Mechanism Fine-tuning
Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Guangdong Institute of Smart Education, Jinan University(暨南大学广东智慧教育研究院);TAL Education Group(好未来教育集团)