SOURCE-LINKED INTELLIGENCE

When Tool Outputs Become Commands: Separating Action Induction from Runtime Authorization in Tool-Augmented LLM Agents

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Tool-augmented LLM agents must rely on untrusted runtime Observations to complete open-ended tasks; however, when tool outputs no longer merely provide data but begin to specify concrete actions, they effectively become ``commands'' that can drive real-world side effects beyond user intent. We argue that this risk arises from conflating action induction with execution authorization. To address this distinction, we propose SARA, which treats action induction and execution authorization as distinct runtime roles and separates action provenance from execution authority. On the Observation side, a

Read original source ↗ Open in workspace

recordType

paper

region

Global