军事指挥控制中智能体AI系统的测试与评估

AI 摘要

该研究通过审查240项测试与评估实践，识别出军事指挥控制中智能体AI系统测试所依赖的八项假设，并指出智能体特性削弱了这些假设，导致测试结果无法充分推断实际部署行为。研究提出十项保证声明，并认为在限定任务包线、轨迹正确性等条件下可恢复部分信心，同时部分证据负担需转移至部署阶段。

正文节选

Testing and Evaluation of Agentic AI Systems In Military Command and Control Abstract Agentic AI systems are being procured for military command and control (C2) under public commitments to rigorous testing and human oversight. Whether such commitments can be discharged depends on their supporting assurance case, which requires three elements: claims specifying the conditions for acceptability, evidence bearing on those claims, and an argument connecting the two. Through a structured review of 2

发布时间：2026-08-24 12:00

抓取时间：2026-08-24 14:24

来源机构：arXiv