Toward Vibe Medicine: A Self-Evolving Multi-Agent Framework for Clinical Decision Support

2026-04-01

Meta-Radiology

AI Summary

This work proposes VIBEMed, a multi-agent framework for clinical decision support that overcomes the limitations of static knowledge and rigid workflows in existing systems by enabling dynamic learning from clinician-patient interactions. VIBEMed integrates three specialized agents—hypothesis generation, treatment planning, and knowledge evolution—to synergistically process multimodal clinical data and deliver personalized decisions driven by longitudinal feedback. The framework introduces, for the first time, continuous self-evolution capabilities at the levels of memory, behavior, and strategy, combining large language models, knowledge distillation, and a secure sandboxing mechanism. Evaluated in complex clinical scenarios such as oncology treatment planning, VIBEMed demonstrates substantially improved end-to-end decision performance, particularly excelling in tasks requiring integrative judgment and long-term strategic reasoning.

Abstract

In recent years, the advances of large language models and autonomous agents have revolutionized the healthcare field, facilitating diagnosis and improving treatment results. However, most existing AI systems rely on pre-trained knowledge and predefined pipelines, which struggle to learn dynamically from the interactive chat session history that contains patient outcomes and past failures. To address this limitation, we propose VIBEMed, a multi-agent framework with a built-in self-evolution mechanism and architecture-level safety sandbox for robust clinical decision support. The system integrates three specialized agents, including a Clinical Diagnostic Agent (CDA) for hypothesis generation, a Therapeutic Execution Agent (TEA) for treatment planning, and a Clinical Evolution Manager Agent (CEMA) that distills longitudinal clinical feedback into reusable knowledge, transforming multimodal patient information into personalized medical decisions. Through self-evolution mechanism, the framework enables iterative updates across memory, model behavior, and decision strategies, allowing the system to improve over time. Experimental results show that VIBEMed demonstrates superior performance through its evolving mechanism in complex clinical cases, particularly in tasks that require integrated decision-making and longitudinal planning. The framework also supports reliable end-to-end decisions in challenging scenarios such as oncology treatment planning, highlighting its feasibility in real-world clinical contexts. Overall, VIBEMed provides a practical path beyond static AI systems toward adaptive, experience-driven clinical decision support, demonstrating the value of combining multi-agent collaboration with continuous evolution for advancing precision medicine.

Problem

• clinical decision support
• dynamic learning
• interactive chat history
• longitudinal feedback
• adaptive AI

Innovation

• self-evolving
• multi-agent framework
• clinical decision support
• longitudinal feedback
• precision medicine