Agentic Teaching: AI Agents that Plan, Adapt and Teach over Time
Abstract
Most AI tutors today are reactive: a student asks a question and a chatbot answers. Good teaching, however, is a long-term process: a teacher plans a sequence of activities, observes how a student responds, and adapts. AI agents, i.e. systems that can plan and act towards goals over many steps, now make this kind of teaching technically possible. This project will design and evaluate agentic teachers that model each learner's progress, plan what to teach next, and operate within pedagogical and safety constraints. It combines reinforcement learning, control theory and learning science, with deployment on 海角社区's Lambda Feedback platform.
How to Apply
Please contact Dr Pietro Ferraro if you are interested in applying for this project.
For more information on submitting a PhD application, please consult our application pages here. When you submit your application, please cite this project title in the 'how you are planning to fund your PhD' section.
The deadline for submitting your application is 11 January 2027.