Scaling AI Safely with Bounded Multi-Agent Systems
ACM AI Letters · 2026-11-11
DOI: 10.1145/3857918 ↗At a glance
Journal article in ACM AI Letters, published online on 2026-11-11. Written by Nicholas Bishop and 5 co-authors. 130 references.
Abstract (original language)
The frontier of AI research is dominated by highly capable, resource-hungry, general-purpose, monolithic agents, which pose significant safety risks that are difficult to mitigate. We argue for a greater focus on studying and building specialised, narrow AI agents, whose capabilities are intentionally limited with safety and efficiency in mind. Moreover, we argue that scaling the deployment of AI in society can be achieved more safely and efficiently through multi-agent systems comprised of such agents. We refer to such systems as bounded multi-agent systems (BMAS). We present a case for BMAS and discuss the outstanding technical challenges and novel safety risks they pose.
Cite
APA
Bishop, N., Ornia, D. J., Hyland, D., Dyer, J., Calinescu, A., & Wooldridge, M. (2026). Scaling AI Safely with Bounded Multi-Agent Systems. ACM AI Letters. https://doi.org/10.1145/3857918
Vancouver
Bishop N, Ornia DJ, Hyland D, Dyer J, Calinescu A, Wooldridge M. Scaling AI Safely with Bounded Multi-Agent Systems. ACM AI Letters. 2026. doi:10.1145/3857918
BibTeX
@article{Bishop2026,
author = {Bishop, Nicholas and Ornia, Daniel Jarne and Hyland, David and Dyer, Joel and Calinescu, Anisoara and Wooldridge, Michael},
title = {Scaling AI Safely with Bounded Multi-Agent Systems},
journal = {ACM AI Letters},
year = {2026},
doi = {10.1145/3857918}
}
EUVIMED