发表机构
School of Electronics, Peking University（电子学院，北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出令牌服务接口（TSI），为AI原生RAN中的令牌流定义服务、时间与状态语义，并通过无人机巡检案例验证其重要性感知资源分配与状态迁移策略。
AI 中文摘要
生成式与具身AI服务在持续的推理与控制循环中交换令牌流。其通信需求取决于每个令牌集的用途、有效时序及执行上下文。本文将这些属性组织为服务语义、时间语义和状态语义，并提出一种位于应用、无线接入网（RAN）与边缘运行时之间的令牌服务接口（TSI）。TSI将交付需求、就绪预测和执行状态引用绑定到每个可调度的令牌集，并明确字段所有权、版本化更新及准入反馈。基于解耦RAN的无人机巡检案例研究展示了重要性感知的无线资源分配、为及时交付而进行的提前准备，以及在中断与转发延迟之间取得平衡的选择性状态迁移。
英文摘要
Generative and embodied AI services exchange token streams within continuing inference and control loops. Their communication requirements depend on each token set's purpose, useful timing, and execution context. This article organizes these properties into service, temporal, and stateful semantics and proposes a token service interface (TSI) between applications, radio access networks (RANs), and edge runtimes. TSI binds delivery requirements, readiness forecasts, and execution-state references to each schedulable token set, specifying field ownership, versioned updates, and admission feedback. A drone inspection case study over a decoupled RAN illustrates importance-aware radio allocation, advance preparation for timely delivery, and selective state migration that balances interruption against forwarding delay.
