The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Orchestrated multi agents sustain accuracy under clinical-scale workloads compared to a single agent
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
MIMIC-IV, a freely accessible electronic health record dataset
Johnson, A. E. W., Bulgarelli, L., Shen, L., Gayles, A., Shammout, A., Horng, S., Pollard, T. J., Hao, S., Moody, B., Gow, B., et al. (2023) · Scientific Data · doi:10.1038/s41597-022-01899-x · Cited by 3,401
Lost in the Middle: How Language Models Use Long Contexts
Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., & Liang, P. (2023) · arXiv · doi:10.48550/arxiv.2307.03172 · Cited by 1,599
Building a knowledge graph to enable precision medicine
Chandak, P., Huang, K., & Zitnik, M. (2023) · Scientific Data · doi:10.1038/s41597-023-01960-3 · Cited by 522
Towards conversational diagnostic artificial intelligence
Tu, T., Schaekermann, M., Palepu, A., Saab, K., Freyberg, J., Tanno, R., Wang, A., Li, B., Amin, M., Cheng, Y., et al. (2025) · Nature · doi:10.1038/s41586-025-08866-7 · Cited by 366 · cited 3×
“AMIE, published in Nature, showed that a single dialogue ‑ optimised LLM can match physicians in simulated consultations 3 .”
Retrieval augmented generation for large language models in healthcare: A systematic review
Amugongo, L. M., Mascheroni, P., Brooks, S., Doering, S., & Seidel, J. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000877 · Cited by 267 · cited 1×
“…a fi xed overhead (orchestrator + worker calls and repeated prompts), which can increase total tokens and latency at smaller batch sizes for some checkpoints; however, as batch size grows, task partitioning prevents context-driven degradation and yields more predictable scaling under load.”
Sociodemographic biases in medical decision making by large language models
Omar, M., Soffer, S., Agbareia, R., Bragazzi, N. L., Apakama, D. U., Horowitz, C. R., Charney, A. W., Freeman, R., Kummer, B., Glicksberg, B. S., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03626-6 · Cited by 173
Self-citationEvaluating large language models as agents in the clinic
Mehandru, N., Miao, B. Y., Almaraz, E. R., Sushil, M., Butte, A. J., & Alaa, A. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01083-y · Cited by 143
Research works printed but not linked: 3
- Bosma, J. S. et al. The DRAGON benchmark for clinical NLP. npj Digit. Med. 8, 289 (2025). · DOI
- Klang, E. et al. A strategy for cost-effective large language model use at health system-scale. npj Digit. Med. 7, 320 (2024). · DOI
- Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172–180 (2023). · DOI · Paper page
Metadata
- Authors
- Klang, E., Omar, M., Raut, G., Agbareia, R., Timsina, P., Freeman, R., Gavin, N., Stump, L., Charney, A. W., Glicksberg, B. S., & Nadkarni, G. N.
- Venue
- npj Health Systems
- Published
- 2026-03-09
- Volume
- 3
- Issue
- 1
- ISSN
- 3005-1959
- Cited by
- 5
- References
- 7
- Language
- en
- Licence
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Funders
- Scientific Computing and Data at the Icahn School of Medicine at Mount Sinai (UL1TR004419)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Orchestrated multi agents sustain accuracy under clinical-scale workloads compared to a single agent. https://app.cochat.ai/papers/10.1038/s44401-026-00077-0
- The paper
- Klang, E., Omar, M., Raut, G., Agbareia, R., Timsina, P., Freeman, R., Gavin, N., Stump, L., Charney, A. W., Glicksberg, B. S., & Nadkarni, G. N. (2026). Orchestrated multi agents sustain accuracy under clinical-scale workloads compared to a single agent. npj Health Systems. https://doi.org/10.1038/s44401-026-00077-0
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.