面向 Agentic AI 系统的不确定性感知资源编排
Uncertainty-Aware Resource Orchestration for Agentic AI Systems
AI 导读
一项被 IEEE MECOM 2026 录用的研究提出 CRO（Conformal Reservation for Orchestration）算法，在调度时为 LLM 智能体流水线预留计算与带宽资源。
正文 · 原文
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 latency demands of such pipelines are unknown at dispatch time: they emerge at runtime from intermediate observations and stochastic token sampling, yielding heavy-tailed, multi-modal random variables. This unpredictability forces infrastructure orchestrators into a dilemma: under-provisioning risks mid-execution throttling and deadline violations, while over-provisioning wastes scarce edge or cloud capacity. Existing schedulers require a fully known pipeline graph, while edge resource-management methods rely on parametric or stationary demand models, and neither fits the unknown, non-stationary profiles of agentic pipelines. We formalize this setting as the uncertainty-aware agentic orchestration problem, where the goal is to reserve, at dispatch time, compute and bandwidth allocations that cover actual pipeline demands, and to verify that the pipeline can meet its deadline, each with a prescribed probability. We then propose Conformal Reservation for Orchestration (CRO), an online algorithm that translates a sliding window of past execution traces into dispatch-time resource allocations with finite-sample, distribution-free coverage guarantees via conformal prediction. Simulations over heterogeneous task mixes with multi-modal and heavy-tailed profiles show that CRO is the only evaluated method that simultaneously satisfies target probabilistic coverage across all risk levels while, among coverage-feasible methods, attaining the lowest over-reservation, roughly halving the resource waste of the Chebyshev-bound baseline.
| Comments: | 6 pages, 2 figures. Accepted to IEEE MECOM 2026, Marrakech, Morocco, 2-4 November 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Networking and Internet Architecture (cs.NI) |
| Cite as: | arXiv:2611.05392 [cs.AI] |
| (or arXiv:2611.05392v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05392 arXiv-issued DOI via DataCite |
Submission history
From: Masoud Shokrnezhad [view email]
[v1]
Mon, 14 Sep 2026 09:30:19 UTC (646 KB)
来源：arXiv cs.AI · arxiv.org