Reinventing Clinical Dialogue: Agentic Paradigms for LLM Enabled Healthcare Communication

TL;DR

This paper explores a paradigm shift in medical AI from reactive language models to agentic systems with reasoning and memory, aiming to improve clinical dialogue's accuracy and empathy.

Contribution

It introduces a novel taxonomy and first-principles analysis of agentic architectures for healthcare communication, highlighting trade-offs between creativity and reliability.

Findings

Categorizes four archetypes of agentic models: Latent Space Clinicians, Emergent Planners, Grounded Synthesizers, Verifiable Workflow Automators.

Provides a systematic analysis of technical components like planning, memory, and execution in clinical AI systems.

Reveals how architectural choices impact safety and autonomy in healthcare AI applications.

Abstract

Clinical dialogue represents a complex duality requiring both the empathetic fluency of natural conversation and the rigorous precision of evidence-based medicine. While Large Language Models possess unprecedented linguistic capabilities, their architectural reliance on reactive and stateless processing often favors probabilistic plausibility over factual veracity. This structural limitation has catalyzed a paradigm shift in medical AI from generative text prediction to agentic autonomy, where the model functions as a central reasoning engine capable of deliberate planning and persistent memory. Moving beyond existing reviews that primarily catalog downstream applications, this survey provides a first-principles analysis of the cognitive architecture underpinning this shift. We introduce a novel taxonomy structured along the orthogonal axes of knowledge source and agency objective to delineate the provenance of clinical knowledge against the system's operational scope. This framework facilitates a systematic analysis of the intrinsic trade-offs between creativity and reliability by categorizing methods into four archetypes: \textit{Latent Space Clinicians}, \textit{Emergent Planners}, \textit{Grounded Synthesizers}, and \textit{Verifiable Workflow Automators}. For each paradigm, we deconstruct the technical realization across the entire cognitive pipeline, encompassing strategic planning, memory management, action execution, collaboration, and evolution to reveal how distinct architectural choices balance the tension between autonomy and safety.