The field of medical reasoning models is experiencing significant advancements, with a focus on improving the accuracy and reliability of clinical decision-making systems. Researchers are developing innovative approaches to verify intermediate reasoning steps against established medical knowledge bases, enabling more precise assessments of reasoning quality. These developments have the potential to enhance patient care and improve diagnosis accuracy. Noteworthy papers in this area include Med-PRM, which achieves state-of-the-art performance on medical QA benchmarks by verifying reasoning steps against clinical guidelines and literature. Another notable work is Med-REFL, which proposes a tree-of-thought approach to decompose medical questions into fine-grained reasoning paths, enabling automatic construction of direct preference optimization data and improving model performance.