9 papers
AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
Yulei Ye, Wenhao Li, Zhong Wen +23
Despite the rapid deployment of LLMs into classrooms, validating educational AI remains uniquely intractable: interventions act on developing learners whose cognitive and social tr…
Edu-MMBias: A Three-Tier Multimodal Benchmark for Auditing Social Bias in Vision-Language Models under Educational Contexts
Ruijia Li, Mingzi Zhang, Zengyi Yu +2
As Vision-Language Models (VLMs) become integral to educational decision-making, ensuring their fairness is paramount. However, current text-centric evaluations neglect the visual…
SLOW: Strategic Logical-inference Open Workspace for Cognitive Adaptation in AI Tutoring
Yuang Wei, Ruijia Li, Bo Jiang
While Large Language Models (LLMs) have demonstrated remarkable fluency in educational dialogues, most generative tutors primarily operate through intuitive, single-pass generation…
Thinking in Graphs with CoMAP: A Shared Visual Workspace for Designing Project-Based Learning
Ruijia Li, Bo Jiang
Designing project-based learning (PBL) demands managing highly interdependent components, a task that both traditional linear tools and purely conversational AI struggle with. Trad…
DiaCDM: Cognitive Diagnosis in Teacher-Student Dialogues using the Initiation-Response-Evaluation Framework
Rui Jia, Yuang Wei, Ruijia Li +5
While cognitive diagnosis (CD) effectively assesses students' knowledge mastery from structured test data, applying it to real-world teacher-student dialogues presents two fundamen…
How Real Is AI Tutoring? Comparing Simulated and Human Dialogues in One-on-One Instruction
Ruijia Li, Yuan-Hao Jiang, Jiatong Wang +1
Heuristic and scaffolded teacher-student dialogues are widely regarded as critical for fostering students' higher-order thinking and deep learning. However, large language models (…