We call for the development of agentic systems that thrive in new environments. Agentic systems, comprising foundation models, tools, and an execution strategy, have demonstrated strong capabilities, yet their development is often constrained by narrow benchmarks and their operation is siloed to limited environments. This paper advocates for developing general, adaptive agents that excel across diverse environments, from terminals and web interfaces to biological and embodied settings. We examine current limitations, explain the potential of increased generality, and identify immediate development priorities. Finally, we argue that protocols and evaluation must prioritize adaptiveness to foster a shared ecosystem for general-purpose agentic systems.
@misc{bandel2026agentic,
title = {Position: Agentic Systems Should be General},
author = {Bandel, Elron and Yehudai, Asaf and Lacoste, Alexandre and Ghosh, Avijit and Neubig, Graham and Mitchell, Margaret and Shmueli-Scheuer, Michal and Choshen, Leshem},
year = {2026},
month = feb,
note = {14 pages. Posted 18 Feb 2026},
institution = {SSRN},
howpublished = {\url{https://ssrn.com/abstract=6176178}},
abstract = {We call for the development of agentic systems that thrive in new environments. Agentic systems, comprising foundation models, tools, and an execution strategy, have demonstrated strong capabilities, yet their development is often constrained by narrow benchmarks and their operation is siloed to limited environments. This paper advocates for developing general, adaptive agents that excel across diverse environments, from terminals and web interfaces to biological and embodied settings. We examine current limitations, explain the potential of increased generality, and identify immediate development priorities. Finally, we argue that protocols and evaluation must prioritize adaptiveness to foster a shared ecosystem for general-purpose agentic systems.},
url = {https://ssrn.com/abstract=6176178}
}
See the full reference list in the paper.