📄 中文摘要
实时人工智能服务在设备-边缘-云的连续体上日益普及，自治的人工智能代理生成延迟敏感的工作负载，协调多阶段处理管道，并在政策和治理约束下竞争共享资源。服务依赖图的结构，建模为有向无环图（DAG），其节点代表计算阶段，边表示执行顺序，是去中心化、基于价格的资源分配在大规模下能否可靠运行的主要决定因素。当依赖图呈现层次结构（树或系列并行）时，价格会收敛到稳定均衡，最优分配可以高效计算，并且在适当的机制设计下（具有准线性特性），资源分配的效率和稳定性得以保障。
实时人工智能服务经济：跨越连续体的自主计算框架
📄 English Summary
Real-Time AI Service Economy: A Framework for Agentic Computing Across the Continuum
Real-time AI services are increasingly prevalent across the device-edge-cloud continuum, where autonomous AI agents generate latency-sensitive workloads, orchestrate multi-stage processing pipelines, and compete for shared resources under policy and governance constraints. The structure of service-dependency graphs, modeled as directed acyclic graphs (DAGs) with nodes representing compute stages and edges encoding execution ordering, is a primary determinant of the reliability of decentralized, price-based resource allocation at scale. When dependency graphs are hierarchical (tree or series-parallel), prices converge to stable equilibria, optimal allocations can be computed efficiently, and under appropriate mechanism design (with quasilinear properties), the efficiency and stability of resource allocation are ensured.