Back

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

Omar, M.; Klang, E.; Ganesh, J.; Agbareia, R.; Tsimina, P.; Freeman, R.; Gavin, N.; Stump, L.; Charney, A. W.; Glicksberg, B. S.; Nadkarni, G.

2025-08-24 health informatics
10.1101/2025.08.22.25334049 medRxiv
Show abstract

We tested state-of-the-art large language models (LLMs) in two configurations for clinical-scale workloads: a single agent handling heterogeneous tasks versus an orchestrated multi-agent system assigning each task to a dedicated worker. Across retrieval, extraction, and dosing calculations, we varied batch sizes from 5 to 80 to simulate clinical traffic. Multi-agent runs maintained high accuracy under load (pooled accuracy 90.6% at 5 tasks, 65.3% at 80) while single-agent accuracy fell sharply (73.1% to 16.6%), with significant differences beyond 10 tasks (FDR-adjusted p < 0.01). Multi-agent execution reduced token usage up to 65-fold and limited latency growth compared with single-agent runs. The designs isolation of tasks prevented context interference and preserved performance across four diverse LLM checkpoints. This is the first evaluation of LLM agent architectures under sustained, mixed-task clinical workloads, showing that lightweight orchestration can deliver accuracy, efficiency, and auditability at operational scale.

Published in npj Health Systems · not in our set (fewer than 10 published preprints to learn from) · training set

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.