paper-with-me

홈 › Papers

Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial Intelligence

2026-05-28 · Yanan Wang, Shuaicong Hu, Jian Liu, Guohui Zhou, Aiguo Wang, Cuiwei Yang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.29744

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Picking the Right Specialist: Attentive Neural Process-based Selection of Task-Specialized Models as Tools for Agentic Healthcare Systems

2026-02-16 · Pramit Saha, Joshua Strong, Mohammad Alsharid, Divyanshu Mishra 외 arxiv

Task-specialized models form the backbone of agentic healthcare systems, enabling the agents to answer clinical queries across tasks such as disease diagnosis, localization, and report generation. Yet, for a given task, …

Visual Grounding

Divide, Deliberate, Decide: A Multi-Agent Framework for Fine-Grained Egocentric Action Recognition

2026-06-16 · Alessandro Sottovia, Alessandro Torcinovich, Oswald Lanz arxiv

Fine-grained action recognition in egocentric video is challenging for Vision-Language Models (VLMs): actions often differ only in small visual cues, and a single model tends to be biased toward a subset of these cues. W…

Zero-Shot Action Recognition

STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning

2026-05-11 · Ruiyi Yang, Lihuan Li, Hao Xue, Flora D. Salim arxiv

Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, and trajectory agents. A central question is how such a system should…

FeatureHospital: A Skill-Driven Multi-Agent Framework for Automated Algorithm Customization in Multi-View Multi-Label Feature Selection

2026-08-17 · Junxuan Li, Zhiqi Chen, Yuzhou Liu, Peng Zhang 외 arxiv

Multi-view multi-label feature selection aims to identify a compact and informative feature subset from heterogeneous views while preserving discriminative information for multiple labels. Existing methods are generally …

When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry Analysis

2026-07-17 · S. Aaron McClendon arxiv

Model merging is promoted as a substitute for joint multi-task training, yet in the reinforcement-learning setting this substitution is essentially never tested against the baseline it claims to replace: methods merge in…

Reinforcement Learning