Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning

Doctor-R1 is a new AI agent that combines accurate medical decision-making with strategic, empathetic patient consultation skills through reinforcement learning. The system outperforms existing open-source medical LLMs and proprietary models on clinical benchmarks while demonstrating superior communication quality and patient-centric performance.

• →Doctor-R1 addresses the gap in existing medical LLMs that lack strategic consultation and empathy skills despite good diagnostic accuracy.
• →The framework uses a multi-agent environment, two-tiered reward system, and experience repository to train both clinical and communication abilities.
• →Doctor-R1 outperforms state-of-the-art open-source medical LLMs with higher parameter efficiency.
• →Human expert evaluations confirm superior clinical capability and patient-centric performance compared to existing models.
• →The system demonstrates the potential for AI to handle complex multi-turn medical consultations beyond simple diagnosis.