发表机构
Lamarr Institute; Fraunhofer IAIS（Lamarr 研究所; 弗劳恩霍夫智能分析与信息系统研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文利用大语言模型自主编写紧凑、可解释的时间序列异常检测程序，在TSB-AD基准上超越强基线，无需训练网络或GPU，实现精度、效率与可解释性的统一。
AI 中文摘要
时间序列异常检测需要在预测精度、计算效率和可解释性之间进行权衡。我们不是将大语言模型用作检测器，而是将其用作检测器的编写者：一个自主研究循环，在该循环中，模型在无泄漏目标下反复编辑单个简短的NumPy程序，并保留其发现的最佳评分检测器。该循环发现了两个紧凑的检测器，一个用于单变量序列，另一个用于多变量序列，它们通过局部频谱特征描述短窗口，并通过协方差感知距离与训练区域分布进行比较。在TSB-AD基准上，这些检测器在各项指标上领先，超过了包括Time-RCD在内的最强经典、深度和基础模型基线，然而它们不训练网络，不使用GPU，并且多变量检测器比每个性能相近的基线都快。因此，LLM驱动的程序搜索是获得准确、高效和透明检测器的实用途径。
英文摘要
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.
