arXiv cs.AI· Bing Hu, Rishabh Sharma·· 12 小时前AI 评分34
Taurus：LLM 在环的 CT 标注以一半成本追平编码智能体
Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost
AI 导读
研究团队构建了 CT 标注工具 Taurus，通过自动化标注加模型复核的流程，在 6 个公开数据集共 939 个 CT 体积上与自由编写分割代码的智能体对比。最终版 Taurus 在主要指标上与使用 Claude Opus 5.5 的自由智能体无差异，且表面平滑度匹配人工参考，单例成本为 $1.22 对 $2.71。作者指出，Taurus 的竞争力主要来自工具框架与自动化流程，而非语言模型本身。
正文 · 原文
Abstract:Dense labels of the aorta in CT are slow to draw, and the public aortic CT datasets that could stand in for them each label different structures under their own conventions. Large language model (LLM) agents can now write code and read images. We asked whether such a model labels these scans better as a free-form agent that writes its own segmentation code, or inside a harness, where an automated pass labels the scan and the model reviews the result. We built a harness, Taurus, and compared it with free-form agents by blind label recovery: we withheld the human labels of six public datasets (939 volumes) and scored every approach against each dataset's own classes. In the first version of Taurus, the model's review raised the primary metric on only two of six datasets, by less than the noise between two reviews of the same case. A free-form agent running Claude Opus 5.5 scored higher on most datasets. Moving what the free-form agents did well into the automated pass then carried most of the gain on 38 held-out cases. The final version smooths the label surfaces with a fixed rule and checks for the large errors the automated pass tends to make, such as an aneurysm drawn to half its size. Each check that fires puts a multiple-choice question to the model, with candidate corrections drawn on the scan. It matched the surface smoothness of the human references, and in the primary metric we found no difference from the free-form Opus agent, at under half its cost, $1.22 against $2.71 per case. Most of what made Taurus competitive came from the harness and its automation rather than from the language model itself. Taurus shows that this kind of annotation can be automated, so that expert time can move from drawing labels to checking them.
| Comments: | 24 pages (10 main text, 12 appendix), 8 figures, 10 tables |
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| ACM classes: | I.4.6; I.2.7; J.3 |
| Cite as: | arXiv:2611.00247 [cs.AI] |
| (or arXiv:2611.00247v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.00247 arXiv-issued DOI via DataCite |
Submission history
From: Bing Hu [view email]
[v1]
Fri, 30 Oct 2026 18:27:53 UTC (3,269 KB)
[v2]
Thu, 5 Nov 2026 03:15:53 UTC (3,224 KB)
来源：arXiv cs.AI · arxiv.org