Skip to content
Agents

One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails.

arXiv:2610.12292v1 Announce Type: new Abstract: A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no text. Recent work places these models in agent systems as gu

arXiv cs.AIResearch source·