Detecting Perspective Shifts in Multi-Agent Systems

Eric W Bridgeford, Hayden Helm
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:9826-9855, 2026.

Abstract

Generative models augmented with external tools and update mechanisms (or agents) have demonstrated capabilities beyond intelligent prompting of base models. As agent use proliferates, dynamic multi-agent systems have naturally emerged. Recent work has investigated the theoretical and empirical properties of low-dimensional representations of agents based on query responses at a single time point. This paper introduces the Temporal Data Kernel Perspective Space (TDKPS), which jointly embeds agents across time, and proposes several novel hypothesis tests for detecting behavioral change at the agent- and group-level in black-box multi-agent systems. We characterize the empirical properties of our proposed tests, including their sensitivity to key hyperparameters, in simulations motivated by a multi-agent system of evolving digital personas. Finally, we demonstrate via natural experiment that our proposed tests detect changes that correlate sensitively, specifically, and significantly with a real exogenous event. TDKPS is the first principled framework for monitoring behavioral dynamics in black-box multi-agent systems – a critical capability as generative agent deployment continues to scale.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-bridgeford26a, title = {Detecting Perspective Shifts in Multi-Agent Systems}, author = {Bridgeford, Eric W and Helm, Hayden}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {9826--9855}, 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/bridgeford26a/bridgeford26a.pdf}, url = {https://proceedings.mlr.press/v306/bridgeford26a.html}, abstract = {Generative models augmented with external tools and update mechanisms (or agents) have demonstrated capabilities beyond intelligent prompting of base models. As agent use proliferates, dynamic multi-agent systems have naturally emerged. Recent work has investigated the theoretical and empirical properties of low-dimensional representations of agents based on query responses at a single time point. This paper introduces the Temporal Data Kernel Perspective Space (TDKPS), which jointly embeds agents across time, and proposes several novel hypothesis tests for detecting behavioral change at the agent- and group-level in black-box multi-agent systems. We characterize the empirical properties of our proposed tests, including their sensitivity to key hyperparameters, in simulations motivated by a multi-agent system of evolving digital personas. Finally, we demonstrate via natural experiment that our proposed tests detect changes that correlate sensitively, specifically, and significantly with a real exogenous event. TDKPS is the first principled framework for monitoring behavioral dynamics in black-box multi-agent systems – a critical capability as generative agent deployment continues to scale.} }
Endnote
%0 Conference Paper %T Detecting Perspective Shifts in Multi-Agent Systems %A Eric W Bridgeford %A Hayden Helm %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-bridgeford26a %I PMLR %P 9826--9855 %U https://proceedings.mlr.press/v306/bridgeford26a.html %V 306 %X Generative models augmented with external tools and update mechanisms (or agents) have demonstrated capabilities beyond intelligent prompting of base models. As agent use proliferates, dynamic multi-agent systems have naturally emerged. Recent work has investigated the theoretical and empirical properties of low-dimensional representations of agents based on query responses at a single time point. This paper introduces the Temporal Data Kernel Perspective Space (TDKPS), which jointly embeds agents across time, and proposes several novel hypothesis tests for detecting behavioral change at the agent- and group-level in black-box multi-agent systems. We characterize the empirical properties of our proposed tests, including their sensitivity to key hyperparameters, in simulations motivated by a multi-agent system of evolving digital personas. Finally, we demonstrate via natural experiment that our proposed tests detect changes that correlate sensitively, specifically, and significantly with a real exogenous event. TDKPS is the first principled framework for monitoring behavioral dynamics in black-box multi-agent systems – a critical capability as generative agent deployment continues to scale.
APA
Bridgeford, E.W. & Helm, H.. (2026). Detecting Perspective Shifts in Multi-Agent Systems. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:9826-9855 Available from https://proceedings.mlr.press/v306/bridgeford26a.html.

Related Material