SOURCE-LINKED INTELLIGENCE

Auto-Policy, not Auto-Skill: Compiled Agent Skills for the Physical World

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Self-evolving Skill harnesses (AutoSkills, Hermes Agent) generate more advisory orchestration automatically; their reported gains are efficiency, not safety. This misses the actual gap: a Skill describes how an agent should behave; a Policy decides which behavior is allowed to become an action. Today's format covers the first with markdown and scripts; the second is left to the model. Generating more Skills scales the gap, not the safety, especially when a wrong invocation can unlock a door or move money. Two adjacent attacks are documented: malicious skills compromising cloud software, and ja

Read original source ↗ Open in workspace

recordType

paper

region

Global