1
Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
面对变幻莫测的AI智能体，这份综述给出规范、验证、执行三层安全防线，是构建可信Agent的必读指南。
arXiv:2608.14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls…