Position: Agentic Systems Should be General

Elron Bandel, Asaf Yehudai, Alexandre Lacoste, Avijit Ghosh, Graham Neubig, Margaret Mitchell, Michal Shmueli-Scheuer, Leshem Choshen

Keywords: agents, agentic systems, generality, bitter lesson, evaluation, agent evaluation, OOD

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.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 176