---
id: 20260913-T0-05
title: "把就绪和发布解耦：面向Agentic LLM工作流的尾延迟调度方案"
title_en: "Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows"
url: https://ai.daily.yangsir.net/daily/20260913-T0-05
issue_date: 2026-09-13
publish_date: 2026-09-12T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2609.10964
---

# 把就绪和发布解耦：面向Agentic LLM工作流的尾延迟调度方案

arXiv论文2609.10964研究Agentic LLM工作流的调度问题。这类工作流由模型轮次和工具交互交替组成，端到端完成时间不仅取决于推理速度，还取决于每个就绪轮次何时被释放。多数运行时立即释放每个轮次，可能导致尾部延迟恶化。论文提出将就绪与发布解耦的调度方法，目标是降低尾延迟。对构建Agent系统的工程师来说，这提供了一个优化端到端响应时间的调度思路。

## English Version

**Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows**

arXiv paper 2609.10964 studies scheduling for agentic LLM workflows, which consist of model turns interleaved with tool interactions. End-to-end completion time depends not only on inference speed but also on when ready turns are released. Most runtimes release each turn immediately, potentially worsening tail latency. The paper proposes decoupling readiness from release for tail-aware scheduling. For engineers building agent systems, this offers a scheduling approach to optimize end-to-end response time.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2609.10964)

**详情页**：https://ai.daily.yangsir.net/daily/20260913-T0-05

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*