RPO-PDT: Demonstrating Role-Play-Based Knowledge Adaptation for Student Support Dialogue (Demonstration System)
2026-06-08 • Robotics
Robotics
AI summaryⓘ
The authors developed RPO-PDT, a dialogue system to help college students by acting like a personal tutor specific to their institution. It uses reliable information sources and follows strict rules to keep conversations safe and private. When the system can't solve a problem, it replays the chat from the student's viewpoint to try different tutoring strategies, which it can remember for future use. This system works both through text and a robot interface called Furhat.
dialogue systemadaptive learningrole-playpersonal development tutorretrieval-groundedstudent supportconfidentiality policiesFurhat robotstrategy memory
Authors
Filip Janik, Ewa Olton, Robert Smales, Harris Spratt, Shea Tait, Md Zia Ullah, Yanchao Yu
Abstract
We present RPO-PDT: a retrieval-grounded, role-play-based dialogue system for adaptive student support in higher education. RPO-PDT is: (1) able to provide institution-specific Personal Development Tutor (PDT) guidance using structured knowledge sources; (2) constrained by explicit persona, boundary, confidentiality, and safety policies; and (3) designed around a reverse-roleplay loop where unresolved interactions are replayed from the student perspective, enabling alternative tutor strategies to be generated and stored as reusable strategy memory. RPO-PDT supports both text-based and Furhat-based embodied interaction for demonstrating grounded, safe, and adaptive student-support dialogue.