Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces HetMedAgent, a multi-agent framework for medical AI that combines generalist LLMs with domain-specific specialist models and clinician input. The framework uses conflict-aware evidence fusion, uncertainty-based clinician intervention, and adaptive threshold calibration to improve clinical decision-making. Experiments on three real-world tasks show that the hybrid approach significantly outperforms either generalist or specialist models alone, highlighting the continued importance of specialist models.
Medical AI's future isn't monolithic LLMs, but a "dream team" of generalists, specialists, and clinicians working together.
The impressive performance of generalist large language models (LLMs) such as GPT and Claude in healthcare raises a critical question: will domain-specific medical specialist models become obsolete? We argue that the future of medical artificial intelligence (AI) lies not in building monolithic medical foundation models, nor in replacing human expertise, but in orchestrating collaboration among generalist LLMs, domain-specific specialist models, and clinicians. We propose HetMedAgent, a heterogeneous medical multi-agent framework that enables conflict-aware evidence fusion, uncertainty-based clinician intervention triggering, and adaptive threshold calibration. Experiments on three real-world clinical decision-making tasks demonstrate that the synergy between generalist LLMs and domain-specific specialist models significantly outperforms using either type of model alone, validating the irreplaceable value of specialist models in modality-specific analysis. HetMedAgent represents a shift from building medical LLMs or foundation models to multi-agent collaboration, achieving a balance between general reasoning capabilities and domain-specific precision.