State of the Field
Current research in educational AI is increasingly focused on enhancing personalized learning experiences through sophisticated frameworks that integrate large language models (LLMs) with adaptive feedback mechanisms. Recent work emphasizes the development of systems like ALIGNAgent, which combines knowledge tracing and resource recommendation to create a continuous feedback loop that addresses individual student needs. Additionally, innovations such as DrawSim-PD and LAVES are leveraging generative models to simulate student artifacts and produce instructional videos, respectively, thereby overcoming data scarcity and production cost challenges. The shift towards hybrid, multi-agent frameworks, as seen in projects like ReQUESTA and ConvoLearn, highlights the importance of cognitive diversity and dialogic learning in educational contexts. These advancements not only improve the quality of educational content but also aim to foster deeper engagement and critical thinking among learners, addressing pressing commercial needs in the education sector for scalable, effective, and personalized learning solutions.
Papers
1–10 of 23Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation
Although recent end-to-end video generation models demonstrate impressive performance in visually oriented content creation, they remain limited in scenarios that require strict logical rigor and prec...
IB-GRPO: Aligning LLM-based Learning Path Recommendation with Educational Objectives via Indicator-Based Group Relative Policy Optimization
Learning Path Recommendation (LPR) aims to generate personalized sequences of learning items that maximize long-term learning effect while respecting pedagogical principles and operational constraints...
DrawSim-PD: Simulating Student Science Drawings to Support NGSS-Aligned Teacher Diagnostic Reasoning
Developing expertise in diagnostic reasoning requires practice with diverse student artifacts, yet privacy regulations prohibit sharing authentic student work for teacher professional development (PD)...
ALIGNAgent: Adaptive Learner Intelligence for Gap Identification and Next-step guidance
Personalized learning systems have emerged as a promising approach to enhance student outcomes by tailoring educational content, pacing, and feedback to individual needs. However, most existing system...
ConvoLearn: A Dataset of Constructivist Tutor-Student Dialogue
In educational applications, LLMs exhibit several fundamental pedagogical limitations, such as their tendency to reveal solutions rather than support dialogic learning. We introduce ConvoLearn (https:...
A Generalized Apprenticeship Learning Framework for Capturing Evolving Student Pedagogical Strategies
Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) have advanced rapidly in recent years and have been successfully applied to e-learning environments like intelligent tutoring systems ...
Cognitively Diverse Multiple-Choice Question Generation: A Hybrid Multi-Agent Framework with Large Language Models
Recent advances in large language models (LLMs) have made automated multiple-choice question (MCQ) generation increasingly feasible; however, reliably producing items that satisfy controlled cognitive...
LLM Prompt Evaluation for Educational Applications
As large language models (LLMs) become increasingly common in educational applications, there is a growing need for evidence-based methods to design and evaluate LLM prompts that produce personalized ...
Dynamic Framework for Collaborative Learning: Leveraging Advanced LLM with Adaptive Feedback Mechanisms
This paper presents a framework for integrating LLM into collaborative learning platforms to enhance student engagement, critical thinking, and inclusivity. The framework employs advanced LLMs as dyna...
Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space
Knowledge Tracing (KT) diagnoses students' concept mastery through continuous learning state monitoring in education.Existing methods primarily focus on studying behavioral sequences based on ID or te...