Researchers from The Chinese University of Hong Kong and the Shenzhen Research Institute of Big Data have introduced HuatuoGPT-o1, a new medical large language model (LLM) designed to enhance advanced medical reasoning. This model employs a two-stage approach that incorporates verifier-guided fine-tuning and reinforcement learning, aiming to improve its ability to solve complex medical problems. HuatuoGPT-o1 is specifically trained for medical applications and excels across various specialist disciplines, addressing the challenges of limited specialist availability and long appointment wait times. The model is available in multiple configurations, including 7B, 8B, 70B, and 72B versions, with the 8B and 70B versions supporting English. The introduction of HuatuoGPT-o1 highlights the potential for improved reasoning capabilities in medical AI applications.