Why Does Agentic Safety Fail to Generalize Across Tasks?

Yonatan Slutzky, Yotam Alexander, Tomer Slor, Yoav Nagel, Nadav Cohen

Abstract

AI agents are increasingly deployed in multi-task settings, where the task to perform is specified at test time, and the agent must generalize to unseen tasks. A major concern in such settings is safety: often, an agent must not only execute unseen tasks, but do so while avoiding risks and handling ones that materialize. Empirical evidence suggests that even when the ability to execute generalizes to unseen tasks, the ability to do so safely frequently does not. This paper provides theory and ex

Categories

Cite This Resource

@article{llmsec202600176,
  title = {Why Does Agentic Safety Fail to Generalize Across Tasks?},
  author = {Yonatan Slutzky and Yotam Alexander and Tomer Slor and Yoav Nagel and Nadav Cohen},
  year = {2026},
  url = {https://arxiv.org/abs/2605.06992},
}