AAAI 2026 第七届智慧教育研讨会 官方主页 https://ai4ed.cc/workshops/aaai2026 AAAI 全称为Association for the Advancement of Artificial Intelligence，是人工智能领域的主要国际学术组织之一。其由计算机科学和人工智能领域奠基人Allen Newell、Marvin Minsky、John McCarthy等学者于1979年共同创立，旨在推动智能思维与行为机制的科学理解及机器实现，并促进人工智能的科学研究和规范应用。 今年AAAI大会的主题是“人工智能赋能教育 - 论多模态大模型（LMMs）在教育中的机遇与挑战”,在人工智能快速发展的时代，多模态大模型在文本、视觉、音频等多领域的理解与生成能力上实现了突破性飞跃。这些模型在教育领域的应用，提供了个性化学习、支持多元化学习需求、自动化复杂教学任务等前所未有的机会。然而，它们在课堂中的实际应用也引发了关于公平性、透明性、可解释性和教学适配性的关键问题。 本次研讨会旨在汇聚领先的专家、教育工作者和决策者，共同探讨LMMs在教育领域的潜力和挑战。通过跨学科对话，活动希望绘制出一条负责任的创新路线，确保这些强大的模型不仅能推动教育成果的提升，还能与教学和学习的核心人类价值观保持一致。 |
会议议程 9:00 AM - 9:45 AM | Keynote Talk one + QA Speaker:Prof. Wenli Chen (Nanyang Technological University) 9:45 AM - 10:30 AM | Oral Session A: AI-Powered Teachable Agents & Learning Interactions ● Does AI-Powered Teachable Agent Benefit Students Evenly? ● When to Stop? An Experimental Study on AI Teachable Agent Stopping Mechanisms ● Learning to Be Taught: A Structured SOEI Framework for Personality-Aligned Virtual Student Agents 10:30 AM - 11:15 AM | Keynote Talk Two + QA Speaker: Dr. Longxiang Huang (Research Scientist, Nanyang Technological University) 11:15 AM - 12:15 PM | Oral Session B: Knowledge Tracing, Personalization & Assessment ● RouteKT: A Knowledge Tracing Framework for Modeling Students’ Problem-Solving Routes ● Reconstruction Attention Positional Encoding for Knowledge Tracing ● Teaching According to Students’ Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs ● Evaluating LLMs as Self-Assessing Educational Agents 12:15 PM - 2:00 PM | Lunch Break 2:00 PM - 2:45 PM | Keynote Talk Three + QA Speaker: Prof. Jiannan Li (Singapore Management University) 2:45 PM - 3:30 PM | Keynote Talk Four + QA Speaker:Mr. Nansong Wang (Vice Principal, ThinkAcademy Singapore) 3:30 PM - 5:00 PM | Oral Session C: Multi-Agent Tutoring & Adaptive Systems ● CoLearn: A Multi-Agent System for Personalized Blended Learning in Higher Education ● AI-Driven Adaptive Tutoring: A Multi-Agent System for Structured, Multimedia-Enhanced Education ● Redefining Educational Simulation: EduVerse as a User-Defined and Developmental Multi-Agent Simulation Space ● MASA: Multi-Agent Guided Interview for Scenario-Based Assessment of Critical Thinking ●Addressing Situated Teaching Needs: A Multi-Agent Framework for Automated Slide Adaptation ● Evaluating LLMs as Self-Assessing Educational Agents 5:00 PM - 6:00 PM | Oral Session D: Multimodal Content Generation & Recommendation ●Multimodal Sequential Recommendation of Online Courses with MLLM-Enhanced Semantic Edge Embedding ● SpeakerTrainer: Multimodal Coaching of Presentation Skills on Mobile Devices ● Teacher-in-the-Loop Story-to-Video: Vision-Language Models and ML Ranking for Educational Content Authoring ● DynaStride: Dynamic Stride Windowing with MMCoT for Instructional Multi-Scene Captioning 入选论文 ● Yinqi Zhang-Kopf, Chenglu Li, Gokhan Gulfidan, Hai Li, Rui Guo. Does AI-Powered Teachable Agent Benefit Students Evenly? A Look at the Relationship between Individual Characteristics and State Mathematical Exam Results. ● Yuxin Liu, Zeqing Song, Jiong Lou, Chentao Wu, Jie Li. AgentTutor: Empowering Personalized Learning with Multi-Turn Interactive Teaching in Intelligent Education Systems. ● Tapiwa Amion Chinodakufa, Ashfaq Ali Shafin, Khandaker Mamun Ahmed. Synthetic Data in Education: Empirical Insights from Traditional Resampling and Deep Generative Models. ● Ding Yu, Yu Lu, Shengquan Yu. RouteKT: A Knowledge Tracing Framework for Modeling Students’ Problem-Solving Routes with Large Language Model. ● Jasper Meynard P. Arana, Kristine Ann M. Carandang, Ethan Robert A. Casin, Daniel Stanley Y. Tan, Christian M. Alis, Christopher P. Monterola. Evaluating LLMs as Self-Assessing Educational Agents: Dual-Role Modeling for Reliable AI-Generated Exams. ● Eddison Pham, Prisha Priyadarshini, Adrian Maliackel, Kanishk Bandi, Cristian Meo, Kevin Zhu. DynaStride: Dynamic Stride Windowing with MMCoT for Instructional Multi-Scene Captioning. ● Zekun Li, Song Li, Ye He, Haoxuan Li, Yikun Jiang, Joy Lim Jia Yin, Daniel Zhang-Li, Shangqing Tu, Yucheng Wang, Yu Zhang, Jifan Yu. MASA: Multi-Agent Guided Interview for Scenario-Based Assessment of Critical Thinking. ● Ju-Yeong Park, Tae-Gwon Lee, Ji-Hoon Bae. Reconstruction Attention Positional Encoding for Knowledge Tracing: Integrating Cognitive Forgetting into Transformer-Based Models. ● Haiping Zhu, Shuaijie He, Ziyu Wang, Qidong Liu, Xinzhu Bai, JiaHao Li, Yan Chen, Nazaraf Shah, Sibo Cai, Feng Tian. Multimodal Sequential Recommendation of On-line courses with MLLM-Enhanced Semantic Edge Embedding. ● Xinmeng Hou, Zhouquan Lu, Wenli Chen, Liang Wan, Feng Wei, Hai Hu, Qing Guo. EduThink4AI: Bridging Educational Critical Thinking and Multi-Agent LLM Systems. ● Yunxuan Lin, Zhengyang Wu, Ronghua Lin, Yong Tang. Context-Driven Learning Path Recommendation: From Static Records to Dynamic Contexts. ● Andrey Savchenko, Anna Slovyagina, Egor Churaev. SpeakerTrainer: Multimodal Coaching of Presentation Skills on Mobile Devices. ● Jayapradeep Jayaraman Srinivas, Riley Phan, Gabriella Campos, Nagendra Chaudhary, Robin Chataut. AI-Driven Adaptive Tutoring: A Multi-Agent System for Structured, Multimedia-Enhanced Education. ● Jaein Kim, Yuna Kim, Juyoung Park, Duk-Jo Kong. Teacher-in-the-Loop Story-to-Video: Vision-Language Models and ML Ranking for Educational Content Authoring. ● Binglin Liu, Yucheng Wang, Zheyuan Zhang, Jiyuan Lu, Shen Yang, Daniel Zhang-Li, Huiqin Liu, Jifan Yu. Addressing Situated Teaching Needs: A Multi-Agent Framework for Automated Slide Adaptation. ● Yang Wu, Rujing Yao, Tong Zhang, Yufei Shi, Zhuoren Jiang, Zhushan Li, Xiaozhong Liu. Teaching According to Students’ Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs. ● Yinqi Zhang-Kopf, Chenglu Li, Gokhan Gulfidan, Hai Li, Yukyeong Song, Rui Guo, Wanli Xing. When to Stop? An Experimental Study on AI Teachable Agent Stopping Mechanisms and Their Learning Affordances in Mathematics. ● Roman Sultimov, Aleksandr Volkov, Tatiana Otbetkina, Mariia Kovalchuk, Melkozerova Yuila, Egor Suraveikin, Maksim Malykh, Yury Maximov. CoLearn: A Multi-Agent System for Personalized Blended Learning in Higher Education. |
组织委员会 ● Zitao Liu Guangdong Institute of Smart Education, Jinan University, China ● Yu Lu Beijing Normal University, China ● Emmanuel G. Blanchard University of Le Mans, France ● Tianqiao Liu TAL Education Group, China |
