This study surveyed higher education practitioners to map their beliefs and behaviors regarding AI integration, finding that while they view AI favorably, institutional barriers and gaps in design-ori…

The paper designs and evaluates a triadic LLM-Teacher collaboration system for K-12 writing, finding that strategic labor division between the LLM and teacher effectively improves writing quality but…

This paper reports the first classroom deployment of LEA, an adaptive AI tutoring agent, with real students across three courses and evaluates its cross-course scalability.

The paper introduces AgentSchool, an advanced LLM-powered multi-agent simulator that models learning as state transitions to provide a robust, ethically viable testbed for educational research and ped…

This paper proposes a source-free continual test-time adaptation methodology using a controlled teacher adaptation and class prototype estimation.

This paper proposes SCOReD, a framework for optimizing chain-of-thought (CoT) distillation in the recommendation domain by parsing teacher traces into typed segments, scoring their importance, and dyn…

This paper introduces the Bridge, a lightweight interface that enables distillation between Teachers and Students with different latent resolutions and VAE spaces in Cross-Space Distillation.

The paper proposes an interpretable, AI-driven decision layer that ranks course topics needing attention using multiple student and teacher signals, successfully identifying learning gaps before forma…

This paper introduces Earthquaker-AI, a hybrid educational framework that combines robotics, rubrics, and AI to enhance earthquake preparedness in primary-school students.

This paper operationalizes knowledge-based design requirements in a generative social robot tutoring system called Teachy Mini, and evaluates its effectiveness in higher education.

This paper presents a large-scale analysis of AI-based learning assistant (Syntea) usage in higher education using log data from 77,543 students.

The paper introduces TeachObs, a comprehensive, human-validated benchmark for multimodal teaching observation, and evaluates frontier LLMs, finding that no single model consistently outperforms others…

This paper reports experiences and takeaways from using puzzles to teach critical testing literacy (CTL) through workshops, introducing the pedagogical framework P4TEST.

This paper introduces Zone of Proximal Policy Optimization (ZPPO) for knowledge distillation, which keeps the teacher inside the student's current zone of development and outperforms off/on-policy dis…

This paper compares two methods for assessing student teams in tabletop exercises using data from learning platforms and evaluates their validity and reliability.

This paper proposes an HPC-aware methodology for Knowledge Distillation (KD) that decouples teacher and student partitioning efficiently, achieving up to 67% higher samples-per-second than the widely…

This paper examines how ChatGPT is framed in educational YouTube videos and investigates the relationship between framings and audience response, using multimodal metadata and Epistemic Network Analys…

This study investigated the stability and prompt-responsiveness of AI tools in classifying the cognitive demand of math tasks, finding that few-shot prompting was a more reliable performance booster t…