面向智能体AI系统的不确定性感知资源编排
原标题：Uncertainty-Aware Resource Orchestration for Agentic AI Systems
AI 摘要
该论文针对由大语言模型驱动的智能体（agentic AI）系统在调度时资源需求未知的问题，提出将计算、带宽和截止时间需求建模为概率机会约束，并给出形式化定义。作者提出在线算法CRO（Conformal Reservation for Orchestration），利用滑动窗口的历史执行轨迹和保形预测，在调度时给出具有有限样本、无分布假设覆盖保证的资源预留。仿真显示，CRO是唯一在所有风险水平下同时满足目标概率覆盖的方法，且过度预留最低，资源浪费约为Chebyshev基线的一半。
正文节选
Uncertainty-Aware Resource Orchestration for Agentic AI Systems Abstract Agentic artificial intelligence (AI) systems powered by large language models (LLMs) execute as autonomous multi-step pipelines that dynamically invoke tools, integrate observations into memory, and iterate until a task is resolved or a resource budget is exhausted. Unlike classical workflows with fixed graphs, the aggregate compute, bandwidth, and end-to-end (E2E) latency demands of such pipelines are unknown at dispatch t