A two-agent structure for enhanced reasoning

Our work addresses this problem with a novel strategy based mostly on the interaction of two LLM-driven brokers, which is analogous to how human clinicians deal with administration issues.

The Dialogue Agent is user-facing and outfitted to quickly reply based mostly on its present understanding of the affected person. This agent handles the conversational facets of the interplay, gathering details about the affected person’s situation, addressing their considerations, and constructing rapport. By leveraging pure language processing and empathetic communication strategies, the Dialogue Agent ensures a seamless and interesting consumer expertise.

The Mx Agent (Administration Reasoning Agent) intentionally and constantly analyzes the out there data, together with scientific tips and patient-specific knowledge, to optimize administration of the affected person. Leveraging Gemini’s state-of-the-art long-context capabilities, this agent synthesizes and causes over giant quantities of data — affected person dialogues throughout a number of visits along with a whole bunch of pages of scientific tips — all of sudden. Utilizing this strategy, it produces structured plans for investigations, remedies, and follow-up care, taking into consideration the newest medical proof, data gathered throughout earlier visits, and particular person affected person preferences.