A curated collection of outstanding papers in AI-era education, covering AI applications in education, theoretical research, and practical exploration.
- Total Papers: 173
- Last Updated: 2025-06-09
- Time Coverage: 2019-2025
- Model Architecture & Training: 35 papers
- Evaluation & Benchmarks: 30 papers
- Intelligent Tutoring Systems: 41 papers
- Learning Analytics & Student Modeling: 20 papers
- Content Generation & Assessment: 19 papers
- Learning Theory & Research: 26 papers
- Teaching Methods & Practice: 2 papers
- MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection
- EduAgent: Generative Student Agents in Learning
- Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation
- Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model
- Self-Explanation in Social AI Agents
- Grammar Control in Dialogue Response Generation for Language Learning Chatbots
- 2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
- Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems
- RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
- PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
- Enhancing the De-identification of Personally Identifiable Information in Educational Data
- Multi-turn Reinforcement Learning from Preference Human Feedback
- A SMART Mnemonic Sounds like “Glue Tonic”: Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick
- LLMs Can Simulate Standardized Patients via Agent Coevolution
- Understanding the World's Museums through Vision-Language Reasoning
- Self-consistency Preference Optimization
- Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
- Student Data Paradox and Curious Case of Single Student-Tutor Model: Regressive Side Effects of Training LLMs for Personalized Learning
- Artificial Human Lecturers: Initial Findings From Asia's First AI Lecturers in Class to Promote Innovation in Education
- Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions
- Prompt Compression for Large Language Models: A Survey
- Students Rather Than Experts: A New AI For Education Pipeline To Model More Human-Like And Personalised Early Adolescences
- RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert Collaboration
- Personalized soups: Personalized large language model alignment via post-hoc parameter merging
- AgentSquare: Automatic LLM Agent Search in Modular Design Space
- A Dual-Fusion Cognitive Diagnosis Framework for Open Student Learning Environments
- From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation
- Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration
- Language Models Learn to Mislead Humans via RLHF
- RAG-Modulo: Solving Sequential Tasks using Experience, Critics, and Language Models
- An overview of domain-specific foundation model: key technologies, applications and challenges
- AI Agent for Education: von Neumann Multi-Agent System Framework
- Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems
- Evaluating the Impact of Advanced LLM Techniques on AI-Lecture Tutors for a Robotics Course
- Automated Feedback for Student Math Responses Based on Multi-Modality and Fine-Tuning
- Towards Responsible Development ofGenerative Al for Education:An Evaluation-Driven Approach
- DrawEduMath: Evaluating Vision Language Models with Expert-Annotated Students' Hand-Drawn Math Images
- Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
- MathFish🐟: Evaluating Language Model Math Reasoning via Grounding in Educational Curricula
- Assessing the Robustness of Retrieval-Augmented Generation Systems in K-12 Educational Question Answering with Knowledge Discrepancies
- Assessing Personalized AI Mentoring with Large Language Models in the Computing Field
- Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors
- Can Large Language Model Agents Simulate Human Trust Behavior?
- Meta-Cognitive Analysis: Evaluating Declarative and Procedural Knowledge in Datasets and Large Language Models
- Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
- Generative AI as a metacognitive agent: A comparative mixed-method study with human participants on ICF-mimicking exam performance
- MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset
- Problem-Oriented Segmentation and Retrieval: Case Study on Tutoring Conversations
- An Exploration of Higher Education Course Evaluation by Large Language Models
- A Survey on Benchmarks of Multimodal Large Language Models
- MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Education
- TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students
- Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
- LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education
- A Systematic Review on Prompt Engineering in Large Language Models for K-12 STEM Education
- Evaluating Explanations Through LLMs: Beyond Traditional User Studies
- A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Education
- Can Large Language Models Generate Middle School Mathematics Explanations Better Than Human Teachers?
- ChatGPT for Education Research: Exploring the Potential of Large Language Models for Qualitative Codebook Development
- Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models
- Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors
- ES-KT-24: A Multimodal Knowledge Tracing Benchmark Dataset with Educational Game Playing Video and Synthetic Text Generation
- Teaching Plan Generation and Evaluation With GPT - 4: Unleashing the Potential of LLM in Instructional Design
- EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios
- EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios
- Position: LLMs Can be Good Tutors in Foreign Language Education
- SocratiQ: A Generative AI-Powered Learning Companion for Personalized Education and Broader Accessibility
- Enhancing Critical Thinking in Education by means of a Socratic Chatbot
- One Size doesn't Fit All: A Personalized Conversational Tutoring Agent for Mathematics Instruction
- Tutorial Dialogue as Adaptive Collaborative Learning Support
- Providing tailored reflection instructions in collaborative learning using large language models
- How Do Students Interact with an LLM-powered Virtual Teaching Assistant in Different Educational Settings?
- Evaluation of an LLM-Powered Student Agent for Teacher Training
- Evaluating the Effectiveness of LLMs in Introductory Computer Science Education: A Semester-Long Field Study
- Transforming Driver Education: A Comparative Analysis of LLM-Augmented Training and Conventional Instruction for Autonomous Vehicle Technologies
- Impact of AI assistance on student agency
- Putting Things into Context: Generative AI-Enabled Context Personalization for Vocabulary Learning Improves Learning Motivation
- The Effects of Embodiment and Personality Expression on Learning in LLM-based Educational Agents
- Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations
- Collaborative Learning with Artificial Intelligence Speakers (CLAIS): Pre-Service Elementary Science Teachers’ Responses to the Prototype
- The use of artificial intelligence (AI) in online learning and distance education processes: A systematic review of empirical studies
- The concept of hybrid human-AI regulation: Exemplifying how to support young learners’ self-regulated learning.
- A robot-based digital storytelling approach to enhancing EFL learners’ multimodal storytelling ability and narrative engagement
- Teachers’ agency in the era of LLM and generative AI: Designing pedagogical AI agents
- Generative Co-Learners: Enhancing Cognitive and Social Presence of Students in Asynchronous Learning with Generative AI
- Enhancing LLM-Based Feedback: Insights from Intelligent Tutoring Systems and the Learning Sciences
- Interactive AI-Generated Virtual Instructors Enhance Learning Motivation and Engagement in Financial Education
- Implementation and Evaluation of Impact on Student Learning of an Automated Platform to Score and Provide Feedback on Constructed-Response Problems in Chemistry
- Empowering student self-regulated learning and science education through ChatGPT: A pioneering pilot study
- AI Teaches the Art of Elegant Coding: Timely, Fair, and Helpful Style Feedback in a Global Course
- Scripted Vicarious Dialogues: Educational Video Augmentation Method for Increasing Isolated Students' Engagement
- Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes
- “Let’s Set Up Some Subgoals”: Understanding Human-Pedagogical Agent Collaborations and Their Implications for Learning and Prompt and Feedback Compliance
- Empowering Private Tutoring by Chaining Large Language Models
- MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education
- GPT-4 as a Homework Tutor can Improve Student Engagement and Learning Outcome
- AI-based learning content generation and learning pathway augmentation to increase learner engagement
- LLMs in Education: Novel Perspectives, Challenges, and Opportunities
- Teachers’ agency in the era of LLM and generative AI
- Towards effective teaching assistants: From intent-based chatbots to LLM-powered teaching assistants
- Large Language Models for Education: A Survey and Outlook
- Empowering Personalized Learning through a Conversation-based Tutoring System with Student Modeling
- Flipped” University: LLM-Assisted Lifelong Learning Environment
- GPTeach: Interactive TA Training with GPT-based Students
- Awaking the Slides: A Tuning-free and Knowledge-regulated AI Tutoring System via Language Model Coordination
- From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents
- Simulating Classroom Education with LLM-Empowered Agents
- Savaal: Scalable Concept-Driven Question Generation to Enhance Human Learning
- Leveraging generative artificial intelligence to simulate student learning behavior
- Edu-ConvoKit: An Open-Source Library for Education Conversation Data
- Transformative Influence of LLM and AI Tools in Student Social Media Engagement: Analyzing Personalization, Communication Efficiency, and Collaborative Learning
- LLM-Driven Ontology Learning to Augment Student Performance Analysis in Higher Education
- What matters in AI-supported learning: A study of human-AI interactions in language learning using cluster analysis and epistemic network analysis
- Behavioral patterns of knowledge construction in online cooperative translation activities
- LLM-based Cognitive Models of Students with Misconceptions
- Student-AI Interaction: A Case Study of CS1 students
- Making AI Accessible for STEM Teachers: Using Explainable AI for Unpacking Classroom Discourse Analysis
- Assessing student-perceived impact of using artificial intelligence tools: Construction of a synthetic index of application in higher education
- Unpacking help-seeking process through multimodal learning analytics: A comparative study of ChatGPT vs Human expert
- Learning at distance: Effects of interaction traces on academic achievement
- Investigating dialogic interaction in K12 online one-on-one mathematics tutoring using AI and sequence mining techniques
- Student engagement and speaking performance in AI-assisted learning environments: A mixed-methods study from Chinese middle schools
- Analytic Frameworks for Assessing Dialogic Argumentation in Online Learning Environments
- The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters’ Exam Performances
- Exploring Knowledge Tracing in Tutor-Student Dialogues
- Towards Mutual Theory of Mind in Human-AI Interaction: How Language Reflects What Students Perceive About a Virtual Teaching Assistant
- Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation
- Educator Attention: How computational tools can systematically identify the distribution of a key resource for students
- Evaluating simulated teaching audio for teacher trainees using RAG and local LLMs
- Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational Domains
- Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring
- PASS: Presentation Automation for Slide Generation and Speech
- A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education
- An Automated Explainable Educational Assessment System Built on LLMs
- Generating AI Literacy MCQs: A Multi-Agent LLM Approach
- TreeQuestion: Assessing Conceptual Learning Outcomes with LLM-Generated Multiple-Choice Questions
- AI-based learning content generation and learning pathway augmentation to increase learner engagement
- Augmented Physics: Creating Interactive and Embedded Physics Simulations from Static Textbook Diagrams
- Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course
- Evaluating and Optimizing Educational Content with Large Language Model Judgments
- Automatic Lesson Plan Generation via Large Language Models with Self-critique Prompting
- The Impact of Example Selection in Few-Shot Prompting on Automated Essay Scoring Using GPT Models
- Towards Human-Like Educational Question Generation with Small Language Models
- Generating Contextualized Mathematics Multiple-Choice Questions Utilizing Large Language Models
- How to Engage Your Readers? Generating Guiding Questions to Promote Active Reading
- Utilizing large language models for EFL essay grading: An examination of reliability and validity in rubric-based assessments
- “My Grade is Wrong!”: A Contestable AI Framework for Interactive Feedback in Evaluating Student Essays
- Human-AI Collaboration: A Student-Centered Perspective of Generative AI Use in Higher Education
- A Proposed Model of Learners' Acceptance and Trust of Pedagogical Conversational AI
- The impact of lay beliefs about AI on adoption of algorithmic advice
- A multidimensional taxonomy for learner-AI interaction
- Artificial intelligence in education: A systematic literature review
- Human-AI Co-Learning for Data-Driven AI
- Exploring the relationship between teachers' professional capital and technology-enhanced teaching innovation: The mediating role of constructivist belief
- Development of the Beliefs about Primary Education Scale: Distinguishing a developmental and transmissive dimension
- What Are They Regulating? Research on Cognitive, Task and Emotional Regulation Patterns in CSCL.
- Artificial intelligence for teaching and learning in schools: The need for pedagogical intelligence
- Social robots and virtual agents as lecturers for video instruction
- Effects of Artificial Intelligence-Powered Virtual Agents on Learning Outcomes in Computer-Based Simulations: A Meta-Analysis
- Influence of Pedagogical Beliefs and Perceived Trust on Teachers’ Acceptance of Educational Artificial Intelligence Tools
- Embracing artificial intelligence in the arts classroom: understanding student perceptions and emotional reactions to AI tools
- What drives students’ AI learning behavior: a perspective of AI anxiety
- Toward constructivism for adult learners in online learning environments
- Improving teacher questioning in science using ICAP theory
- Defending humankind: Anthropocentric bias in the appreciation of AI art.
- AI Composer Bias: Listeners Like Music Less When They Think It Was Composed by an AI
- How Do Strategies for Using ChatGPT Affect Knowledge Comprehension?
- On the relationship between EFL students' attitudes toward artificial intelligence, teachers' immediacy and teacher-student rapport, and their willingness to communicate
- “I feel AI is neither too good nor too bad”: Unveiling Chinese EFL teachers’ perceived emotions in generative AI-Mediated L2 classes
- A Meta-Analysis of the Factor Structure of the Classroom Assessment Scoring System (CLASS)
- Where I feel the most connected:” Community of Inquiry supporting sense of belonging in a HyFlex engineering course
- School Engagement: Potential of the Concept, State of the Evidence
- Assessment and the co-regulation of learning in the classroom
- Qualities of classroom observation systems
- Enhancing Programming Education with ChatGPT: A Case Study on Student Perceptions and Interactions in a Python Course
We welcome high-quality AI education papers! Please ensure:
- Papers are strongly related to AI and education
- From top-tier conferences/journals or arXiv
- Provide accurate metadata (title, authors, links, etc.)
- Include concise summary/comments
For questions or suggestions, please submit an Issue or Pull Request.
⭐ If this project helps you, please give it a Star!
