The field of medical natural language processing is rapidly evolving, with a growing focus on the application of large language models (LLMs) to improve clinical prediction tasks, biomedical research, and patient care. Recent developments have highlighted the potential of LLMs to extract valuable information from unstructured clinical notes, enhancing patient predictions and streamlining biomedical research. Notably, the integration of LLMs with other modalities, such as images, has shown promise in histopathology and other areas. Overall, the field is moving towards more innovative and adaptive solutions, leveraging the capabilities of LLMs to improve healthcare outcomes. Noteworthy papers include: Learning to Be A Doctor: Searching for Effective Medical Agent Architectures, which introduces a novel framework for automated design of medical agent architectures. Paging Dr. GPT: Extracting Information from Clinical Notes to Enhance Patient Predictions, which demonstrates the value of integrating LLMs into clinical prediction tasks. ChatEXAONEPath: An Expert-level Multimodal Large Language Model for Histopathology Using Whole Slide Images, which showcases an expert-level multimodal LLM for histopathology using whole slide images.