MedTutor-R1: Socratic Personalized Medical Teaching with Multi-Agent Simulation

TL;DR

This paper introduces MedTutor-R1, a multimodal Socratic medical tutor trained on a large simulated group instruction dataset, demonstrating improved pedagogical performance and adaptability in clinical education settings.

Contribution

We developed ClinEdu, a multi-agent simulator for complex pedagogical testing, and trained MedTutor-R1, the first multimodal Socratic tutor for group medical instruction, with reinforcement learning.

Findings

MedTutor-R1 outperforms baseline models by over 20% in pedagogical scores.

The model shows high adaptability to varying group sizes.

ClinEdu effectively simulates complex clinical teaching scenarios.

Abstract

The significant gap between rising demands for clinical training and the scarcity of expert instruction poses a major challenge to medical education. With powerful capabilities in personalized guidance, Large Language Models (LLMs) offer a promising solution to bridge this gap. However, current research focuses mainly on one-on-one knowledge instruction, overlooking collaborative reasoning, a key skill for students developed in teamwork like ward rounds. To this end, we develop ClinEdu, a multi-agent pedagogical simulator with personality-driven patients and diverse student cohorts, enabling controlled testing of complex pedagogical processes and scalable generation of teaching data. Based on ClinEdu, we construct ClinTeach, a large Socratic teaching dialogue dataset that captures the complexities of group instruction. We then train MedTutor-R1, the first multimodal Socratic tutor designed for one-to-many instruction in clinical medical education. MedTutor-R1 is first instruction-tuned on our ClinTeach dataset and then optimized with reinforcement learning, using rewards derived from a three-axis rubric, covering structural fidelity, analytical quality, and clinical safety, to refine its adaptive Socratic strategies. For authentic in-situ assessment, we use simulation-based interactive evaluation that redeploys the tutor back into ClinEdu. Experimental results demonstrate that our MedTutor-R1 outperforms the base model by over 20% in average pedagogical score and is comparable to o3, while also exhibiting high adaptability in handling a varying number of students. This promising performance underscores the effectiveness of our pedagogical simulator, ClinEdu.