1
Methods for Formal Verification of Agent Skills: Three Layers Toward a Mechanically Checkable Capability-Containment Proof
三层形式化验证框架，让AI Agent技能边界可机械检查，安全可控。
arXiv:2605.23951v1 Announce Type: new Abstract: The companion paper introduced a four-level verification lattice on agent-skill manifests (unverified,…