Multi-Agent Intelligent Tutoring System

Dr. Setareh Rafatirad
CS Department, UC Davis, Davis, CA

Salazar Hall 2009A
4:00 PM - 5:00 PM

Abstract: As the landscape of Generative AI rapidly expands, there have been several developments in the space of Intelligent tutoring systems, promising the convenience of AI as a supplementary educational tool. But unfortunately, many of these systems fall short by treating pedagogy as a static, one-size-fits-all process. In this study, we propose a multi-agent intelligent tutoring system that dynamically adapts to each student’s emotional affect, cognitive state, and demonstrated mastery on every conversational turn. The brain of our system orchestrates five specialized agents – an emotional affect monitor, a Bayesian Knowledge tracer, a metacognitive agent, a modality generator agent, and a tutoring agent. This unified pipeline produces responses tuned to both what a student knows and how they are feeling in the moment. Knowledge tracing is implemented using Personalized Bayesian Knowledge Tracing (pBKT), a mathematically grounded approach that maintains per-student, per-topic mastery. Retrieval Augment Generation (RAG) grounds all responses in verified material, reducing hallucinations and improving factual accuracy. We evaluate this system using an LLM-as-judge approach with cross-model scoring to help avoid self-preference bias. Our results suggest that structured multi-agent coordination, when backed by established learning principles, offers a scalable path towards truly personalized education.

Bio: Dr. Setareh Rafatirad is an Associate Professor of Teaching in the Department of Computer Science at the UC Davis. She earned her M.S. and Ph.D. in Computer Science from the UC Irvine. Her research focuses on applied machine learning, AI agents, foundation models, AI personalization and reasoning, AI for healthcare, and mobile and IoT security. She currently leads multiple research projects in these areas. Dr. Rafatirad has received research funding from the National Science Foundation (NSF), the Defense Advanced Research Projects Agency (DARPA), and the Air Force Research Laboratory (AFRL). Her recent research on robust and reproducible human evaluation of AI systems was published at the International Conference on Machine Learning (ICML 2026), introducing a novel framework that models annotator disagreement and uncertainty to produce more reliable and statistically grounded evaluations of AI systems. She also received the 2019 ICDM Best Paper Award and was nominated for the ICCAD 2019 Best Paper Award. She is the co-author of the textbook Machine Learning for Computer Scientists and Data Analysts: From an Applied Perspective, which provides a comprehensive introduction to machine learning, covering both theoretical foundations and practical applications—from basic artificial neurons and classical machine learning algorithms to deep neural networks, generative adversarial networks (GANs), and graph neural networks (GNNs).