Orchestrated multi agents sustain accuracy under clinical-scale workloads compared to a single agent

npj Health Systems 2026 Open access

Read full text
Authors: Eyal Klang, Mahmud Omar, Ganesh Raut, Reem Agbareia, Prem Timsina, Robert Freeman, Nicholas Gavin, Lisa Stump, Alexander W. Charney, Benjamin S. Glicksberg, Girish N. Nadkarni
DOI: 10.1038/s44401-026-00077-0
Cited by: 3
References: 9

Abstract

We tested state-of-the-art LLMs under clinical-scale workloads using two designs: a single agent handling all tasks and a multi-agent orchestrator assigning each task to a dedicated worker. Across retrieval, extraction, and dosing tasks, batch sizes ranged from 5-80. Multi-agent accuracy remained high (90.6% at 5 tasks; 65.3% at 80), while single-agent accuracy collapsed (73.1% to 16.6%; p < 0.01). Multi-agent runs used up to 65-fold fewer tokens and limited latency growth. These findings show that lightweight orchestration preserves accuracy and efficiency under mixed-task clinical loads.

Fields of Study & Subjects

Artificial Intelligence in Healthcare and Education Cell Image Analysis Techniques Machine Learning in Healthcare

Publication details

Journal / source
npj Health Systems
Publisher
Springer Science and Business Media LLC
Volume
3
Issue
1
Publication date
9 March 2026
Language
EN