---
id: 20261104-T0-09
title: "Taurus：LLM介入CT标注，效果比肩编程智能体、成本减半"
title_en: "Taurus Matches Coding Agents on CT Annotation at Half the Cost"
url: https://ai.daily.yangsir.net/daily/20261104-T0-09
issue_date: 2026-11-04
publish_date: 2026-11-03T05:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2611.00247
---

# Taurus：LLM介入CT标注，效果比肩编程智能体、成本减半

针对CT影像中主动脉标注耗时、公开数据集标注规范各不相同的问题，研究团队提出Taurus，把LLM引入标注流程。方法利用LLM智能体既能写代码又能读图像的能力，让模型在循环中完成标注任务。结果显示其效果与编程智能体相当，成本仅为后者一半。这为医学影像密集标注提供了一条低成本路径，有望减少人工勾画工作量。

## English Version

**Taurus Matches Coding Agents on CT Annotation at Half the Cost**

Researchers proposed Taurus, an LLM-in-the-loop approach to CT annotation, targeting the slow manual labeling of the aorta and inconsistent conventions across public aortic CT datasets. The method leverages LLM agents that can both write code and read images to perform annotation tasks in a loop. Taurus matches coding agents in performance at half the cost, offering a cheaper route to dense medical imaging labels and potentially reducing manual drawing effort.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2611.00247)

**详情页**：https://ai.daily.yangsir.net/daily/20261104-T0-09

---

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