Position: Behavioral Systems Require Behavioral Tests

Manuel Cherep, Nikhil Singh, Patricia Maes
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:169802-169815, 2026.

Abstract

Artificial agentic systems increasingly operate as behavioral systems by interacting with dynamic environments, pursuing goals, and adapting over time. Yet, current evaluation methods largely focus on performance outcomes, not the underlying behavioral processes that produce them. This paper argues that AI agents must be evaluated like other behavioral systems: through systematic observation, perturbation, and interpretation of their actions. We draw on lessons from the behavioral sciences to motivate this position, and propose a research agenda focused on developing rigorous behavioral tests. These include methods for recovering decision strategies from action sequences, constructing environments that isolate behavioral differences, and probing emergent dynamics in multi-agent systems. Taken together, these directions offer a roadmap for developing a science of AI behavior.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-cherep26b, title = {Position: Behavioral Systems Require Behavioral Tests}, author = {Cherep, Manuel and Singh, Nikhil and Maes, Patricia}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {169802--169815}, 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/cherep26b/cherep26b.pdf}, url = {https://proceedings.mlr.press/v306/cherep26b.html}, abstract = {Artificial agentic systems increasingly operate as behavioral systems by interacting with dynamic environments, pursuing goals, and adapting over time. Yet, current evaluation methods largely focus on performance outcomes, not the underlying behavioral processes that produce them. This paper argues that AI agents must be evaluated like other behavioral systems: through systematic observation, perturbation, and interpretation of their actions. We draw on lessons from the behavioral sciences to motivate this position, and propose a research agenda focused on developing rigorous behavioral tests. These include methods for recovering decision strategies from action sequences, constructing environments that isolate behavioral differences, and probing emergent dynamics in multi-agent systems. Taken together, these directions offer a roadmap for developing a science of AI behavior.} }
Endnote
%0 Conference Paper %T Position: Behavioral Systems Require Behavioral Tests %A Manuel Cherep %A Nikhil Singh %A Patricia Maes %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-cherep26b %I PMLR %P 169802--169815 %U https://proceedings.mlr.press/v306/cherep26b.html %V 306 %X Artificial agentic systems increasingly operate as behavioral systems by interacting with dynamic environments, pursuing goals, and adapting over time. Yet, current evaluation methods largely focus on performance outcomes, not the underlying behavioral processes that produce them. This paper argues that AI agents must be evaluated like other behavioral systems: through systematic observation, perturbation, and interpretation of their actions. We draw on lessons from the behavioral sciences to motivate this position, and propose a research agenda focused on developing rigorous behavioral tests. These include methods for recovering decision strategies from action sequences, constructing environments that isolate behavioral differences, and probing emergent dynamics in multi-agent systems. Taken together, these directions offer a roadmap for developing a science of AI behavior.
APA
Cherep, M., Singh, N. & Maes, P.. (2026). Position: Behavioral Systems Require Behavioral Tests. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:169802-169815 Available from https://proceedings.mlr.press/v306/cherep26b.html.

Related Material