arXiv：cs.LG（机器学习，全量分类）· David Berghaus·· 1 天前AI 评分41
让 LLM 写你的异常检测器：自主发现紧凑可解释的时间序列检测器
Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series
AI 导读
研究者用 LLM 作为异常检测器的作者而非检测器本身，通过自主研究循环反复编辑单个短 NumPy 程序，在无泄漏目标下保留得分最高的检测器，最终发现两个分别面向单变量和多变量序列的紧凑检测器。
正文
Abstract:Time-series anomaly detection trades off predictive accuracy, computational efficiency, and interpretability. We use a large language model not as the detector but as the author of one: an autonomous research loop in which the model repeatedly edits a single short NumPy program under a leakage-free objective, keeping the best-scoring detector it finds. The loop discovers two compact detectors, one for univariate and one for multivariate series, that describe short windows by their local spectral features and compare them with the training-region distribution through a covariance-aware distance. On the TSB-AD benchmark these detectors lead the field across metrics, ahead of the strongest classical, deep, and foundation-model baselines including Time-RCD, yet they train no network and use no GPU, and the multivariate detector is faster than every similarly performing baseline. LLM-driven program search is thus a practical route to accurate, efficient, and transparent detectors.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.01223 [cs.LG] |
| (or arXiv:2610.01223v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01223 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: David Berghaus [view email]
[v1]
Thu, 1 Oct 2026 07:26:09 UTC (695 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org