Researchers propose CRO algorithm to manage unpredictable compute demands of agentic AI systems
Conformal Reservation for Orchestration (CRO) uses past execution traces to reserve compute and bandwidth at dispatch time with finite-sample guarantees, outperforming baselines in simulations of heavy-tailed, multi-modal task profiles.
1 source · cross-referenced
- Agentic AI pipelines driven by LLMs face unpredictable, heavy-tailed compute and bandwidth demands that emerge at runtime.
- Existing schedulers assume fixed graphs or stationary demand models, which do not fit agentic pipelines.
- CRO translates sliding windows of past traces into dispatch-time allocations with distribution-free coverage guarantees via conformal prediction.
- In simulations, CRO is the only method to meet target probabilistic coverage across risk levels while halving resource waste vs. a Chebyshev-bound baseline.
Agentic AI systems powered by large language models 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.
The authors 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.
They 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.
- Nov 11, 2026 · The Verge — AI
Google DeepMind unveils AlphaGenome 2 to predict genetic variant effects on cell types
Trust79 - Nov 11, 2026 · Google DeepMind — Blog
Google DeepMind unveils AlphaGenome 2 to predict DNA variant effects in specific cell types
Trust84 - Nov 11, 2026 · arXiv cs.AI
Researchers demonstrate auditable human-agent teams for autonomous synchrotron X-ray experiments
Trust79