---
id: 20260728-T0-04
title: "CHEST：用分层搜索自动合成智能体工作流，无需大量训练"
title_en: "Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesis"
url: https://ai.daily.yangsir.net/daily/20260728-T0-04
issue_date: 2026-07-28
publish_date: 2026-07-27T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2607.21609
---

# CHEST：用分层搜索自动合成智能体工作流，无需大量训练

arXiv新论文提出CHEST（Coupled Hierarchical Search over Topology and Execution），一种自动合成LLM智能体工作流的方法。现有自动化方法常因搜索空间巨大而陷入僵化、资源密集的离线训练。CHEST通过联合搜索拓扑结构和执行步骤，在无需离线训练的情况下生成高效工作流，显著降低开发门槛。

## English Version

**Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesis**

A new arXiv paper presents CHEST, which automatically synthesizes LLM agent workflows by jointly searching over topology and execution. It avoids the rigid, resource-heavy offline training of prior methods, enabling efficient workflow creation without large-scale compute. Lowers the barrier for building complex agent systems.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2607.21609)

**详情页**：https://ai.daily.yangsir.net/daily/20260728-T0-04

---

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