Position: Multi-Agent Systems Should Prioritize Concurrency Control

Xin Yang, Letian Li, Zimo Ji, Terry Jingchen Zhang, Wenyuan Jiang
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:172725-172740, 2026.

Abstract

LLM-based multi-agent systems (MAS) promise scalable collaboration, yet adding agents often reduces reliability. This position paper argues that many MAS failures are fundamentally concurrency control problems: agents concurrently read and write shared state, and long LLM inference windows amplify the risk of stale reads, lost updates, and inconsistent outcomes. Failure modes commonly attributed to "coordination" or "communication" breakdowns can be mapped directly onto classical concurrency anomalies. Rather than treating these as emergent behaviors to be solved by better prompting or more capable models, we contend that MAS frameworks should incorporate explicit concurrency control mechanisms: conflict detection, isolation guarantees, and structured access to shared resources. Concurrency control should be a first-class design concern, not an afterthought.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-yang26dy, title = {Position: Multi-Agent Systems Should Prioritize Concurrency Control}, author = {Yang, Xin and Li, Letian and Ji, Zimo and Zhang, Terry Jingchen and Jiang, Wenyuan}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {172725--172740}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/yang26dy/yang26dy.pdf}, url = {https://proceedings.mlr.press/v306/yang26dy.html}, abstract = {LLM-based multi-agent systems (MAS) promise scalable collaboration, yet adding agents often reduces reliability. This position paper argues that many MAS failures are fundamentally concurrency control problems: agents concurrently read and write shared state, and long LLM inference windows amplify the risk of stale reads, lost updates, and inconsistent outcomes. Failure modes commonly attributed to "coordination" or "communication" breakdowns can be mapped directly onto classical concurrency anomalies. Rather than treating these as emergent behaviors to be solved by better prompting or more capable models, we contend that MAS frameworks should incorporate explicit concurrency control mechanisms: conflict detection, isolation guarantees, and structured access to shared resources. Concurrency control should be a first-class design concern, not an afterthought.} }
Endnote
%0 Conference Paper %T Position: Multi-Agent Systems Should Prioritize Concurrency Control %A Xin Yang %A Letian Li %A Zimo Ji %A Terry Jingchen Zhang %A Wenyuan Jiang %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-yang26dy %I PMLR %P 172725--172740 %U https://proceedings.mlr.press/v306/yang26dy.html %V 306 %X LLM-based multi-agent systems (MAS) promise scalable collaboration, yet adding agents often reduces reliability. This position paper argues that many MAS failures are fundamentally concurrency control problems: agents concurrently read and write shared state, and long LLM inference windows amplify the risk of stale reads, lost updates, and inconsistent outcomes. Failure modes commonly attributed to "coordination" or "communication" breakdowns can be mapped directly onto classical concurrency anomalies. Rather than treating these as emergent behaviors to be solved by better prompting or more capable models, we contend that MAS frameworks should incorporate explicit concurrency control mechanisms: conflict detection, isolation guarantees, and structured access to shared resources. Concurrency control should be a first-class design concern, not an afterthought.
APA
Yang, X., Li, L., Ji, Z., Zhang, T.J. & Jiang, W.. (2026). Position: Multi-Agent Systems Should Prioritize Concurrency Control. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:172725-172740 Available from https://proceedings.mlr.press/v306/yang26dy.html.

Related Material