Autonomous Pharmaceutical Care with Large Language Models

In modern healthcare systems, physicians often diagnose and prescribe within their specific fields of expertise. However, this compartmentalized approach may not fully assess the overall health condition of patients, leading to potential risks associated with polypharmacy, such as drug-drug interactions. Consequently, pharmaceutical care becomes a critical systemic task, typically managed by clinical pharmacists. Despite their crucial role, clinical pharmacists face challenges in providing personalized medication guidance due to the vast and rapidly evolving body of medical knowledge. With the advancement of artificial intelligence and large language models (LLMs), these technologies have demonstrated significant potential in pharmaceutical care by effectively reducing medication errors and adverse drug events, and alleviating the workload of healthcare professionals. However, existing LLMs still struggle with the accurate interpretation and automated execution of tasks in complex clinical scenarios like pharmaceutical care. To address these challenges, we developed the Shennong-Agent system, a multi-agent framework for LLMs with integrated multimodal inputs. Shennong-Agent is enabled to analyze and segment tasks using chained reasoning and autonomously perform complex pharmacy care tasks using tools such as knowledge retrieval and web search. Rigorously evaluated by medical experts, this system not only surpasses existing LLMs in performance but also enhances its capabilities through reinforcement learning with human feedback.