Journal article · 2026 · Open access
Capable language models can outgrow the benefits of collaboration
Nature Machine Intelligence, 8(7), 1157–1172 · Published 24 July 2026 · DOI 10.1038/s42256-026-01268-y
In brief
“Capable language models can outgrow the benefits of collaboration” is a 2026 journal article by Yubin Kim and 19 co-authors, published in Nature Machine Intelligence. OpenAlex counts 28 citations as of 16 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at Nature Machine Intelligence.
- Citations
- 28
- Most cited in
- 2026 (28)
- Field-weighted impact
- 39.11
- References
- 35
- Authors
- 20
Abstract
Agents, language model-based systems that can reason, plan and act with tools to accomplish tasks, are widely deployed, yet it remains unclear when multi-agent coordination outperforms a strong single agent. Here we conduct a controlled experiment that holds task prompts, tools and compute budgets constant while varying only coordination structure and model capability. Across 260 configurations spanning six benchmarks, five architectures and three LLM families, we derive a predictive model using empirical coordination metrics. Across benchmarks, single-agent baseline performance emerges as the most robust predictor of whether coordination improves or decreases performance. In particular, we identify an empirical capability-saturation threshold beyond which additional agents are unlikely to improve performance. This threshold correctly predicts the effect of multi-agent coordination on performance in 94% of validation configurations on SWE-bench Verified and Terminal-Bench. We therefore interpret this threshold as a practical selection rule rather than a universal scaling principle. A second effect, baseline-scaled error amplification, survives cluster-robust inference (Probust = 0.030) and supports the failure-mode taxonomy. The fitted model achieves cross-validated R2 = 0.373 (0.413 with a task-grounded capability metric) and selects the best architecture in 87% of held-out configurations. These results provide a quantitative framework for within-domain architecture selection and for estimating when multi-agent coordination is likely to improve performance or add overhead. A controlled study of large language model agents across 260 configurations shows when multi-agent collaboration helps or hurts performance, and introduces a predictive model that selects the best architecture in 87% of held-out within-domain configurations.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Kim, Y., Gu, K., Park, C., Park, C., Schmidgall, S., Heydari, A. A., Yan, Y., Zhang, Z., Zhuang, Y., Liu, Y., Malhotra, M., Liang, P. P., Park, H. W., Yang, Y., Xu, X., Du, Y., Patel, S., Althoff, T., McDuff, D., & Liu, X. (2026). Capable language models can outgrow the benefits of collaboration. Nature Machine Intelligence, 8(7), 1157–1172. https://doi.org/10.1038/s42256-026-01268-y
MLA 9
Kim, Yubin, et al. “Capable language models can outgrow the benefits of collaboration.” Nature Machine Intelligence, vol. 8, no. 7, 2026, pp. 1157–1172. https://doi.org/10.1038/s42256-026-01268-y.
Chicago
Kim, Yubin, Ken Gu, Chanwoo Park, Chunjong Park, Samuel Schmidgall, A. Ali Heydari, Yao Yan, et al. 2026. “Capable language models can outgrow the benefits of collaboration.” Nature Machine Intelligence 8 (7): 1157–1172. https://doi.org/10.1038/s42256-026-01268-y.
Harvard
Kim, Y. et al. (2026) ‘Capable language models can outgrow the benefits of collaboration’, Nature Machine Intelligence, 8(7), pp. 1157–1172. doi:10.1038/s42256-026-01268-y.
IEEE
Y. Kim et al., “Capable language models can outgrow the benefits of collaboration,” Nature Machine Intelligence, vol. 8, no. 7, pp. 1157–1172, 2026, doi: 10.1038/s42256-026-01268-y.
BibTeX
@article{kim2026capable,
title = {{Capable language models can outgrow the benefits of collaboration}},
author = {Kim, Yubin and Gu, Ken and Park, Chanwoo and Park, Chunjong and Schmidgall, Samuel and Heydari, A. Ali and Yan, Yao and Zhang, Zhihan and Zhuang, Yuchen and Liu, Yun and Malhotra, Mark and Liang, Paul Pu and Park, Hae Won and Yang, Yuzhe and Xu, Xuhai and Du, Yilun and Patel, Shwetak and Althoff, Tim and McDuff, Daniel and Liu, Xin},
journal = {Nature Machine Intelligence},
year = {2026},
volume = {8},
number = {7},
pages = {1157--1172},
doi = {10.1038/s42256-026-01268-y},
url = {https://doi.org/10.1038/s42256-026-01268-y}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- multi-agent coordination
- LLM agents
- architecture selection
- error amplification
- failure modes
- SWE-bench
- coordination structure
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Kim, Y., Gu, K., Park, C., Park, C., Schmidgall, S., Heydari, A. A., Yan, Y., Zhang, Z., Zhuang, Y., Liu, Y., Malhotra, M., Liang, P. P., Park, H. W., Yang, Y., Xu, X., Du, Y., Patel, S., Althoff, T., McDuff, D., & Liu, X. (2026). Capable language models can outgrow the benefits of collaboration. Nature Machine Intelligence, 8(7), 1157–1172. https://doi.org/10.1038/s42256-026-01268-y
How many times has this paper been cited?
28 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Nature Machine Intelligence: sign in and open the PDF from this page.
Who wrote this paper?
Yubin Kim, Ken Gu, Chanwoo Park, Chunjong Park, Samuel Schmidgall, A. Ali Heydari, Yao Yan, Zhihan Zhang, Yuchen Zhuang, Yun Liu, Mark Malhotra, Paul Pu Liang and 8 more.
What is the DOI of this paper?
10.1038/s42256-026-01268-y, permanently at https://doi.org/10.1038/s42256-026-01268-y. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.