计划变更时：动态多智能体协调的战略世界测试平台
原标题：When the Plan Changes: A Strategic World Testbed for Dynamic Multi-Agent Coordination
AI 摘要
该论文提出名为 Strategic World 的图结构仿真测试平台，用于研究多智能体在目标动态变更时的协调问题。平台将权威目标、本地计划、通知接收与实际行动分离，设计了六类干预场景，并通过脚本化轨迹和本地语言模型试验表明：相同的完成与确认摘要可能掩盖未获知信息下的过时工作、收到通知后仍执行过时任务或受阻的不安全意图。在16个回合的对比中，优先处理待处理通知的防护策略在4/4留出设置中完成，而校准辅助基线仅1/4。
正文节选
When the Plan Changes: A Strategic World Testbed for Dynamic Multi-Agent Coordination Abstract. Changing an objective does not automatically revise agents’ earlier plans or delegated tasks. Acknowledgment can coexist with obsolete execution, while misleading instructions can redirect work or discard retained constraints. We present a Strategic World simulation testbed that separates authoritative objectives, local plans, notice receipt, and consequential action. Six intervention families vary o