Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanatory reasoning required for transparent decision-making. To address these limitations, we propose Time-series Reasoning for Anomaly (Time-RA), a novel task that reformulates TSAD from a discriminative into a generative, reasoning-intensive paradigm. To facilitate this, we introduce RATs40K, the first real-world large-scale multimodal benchmark with ~40,000 samples across 10 domains, integrating raw time series, textual context, and visual plots with structured reasoning annotations. Extensive benchmarking shows that while supervised fine-tuning and visual representations boost diagnostic accuracy and reasoning consistency, performance varies across complex scenarios. Notably, fine-tuned models demonstrate strong "plug-and-play" transferability, outperforming traditional baselines on unseen real-world datasets. Our work establishes a foundation for interpretable, multimodal time series analysis. All code (https://github.com/yyysjz1997/Time-RA) and the RATs40K dataset (https://huggingface.co/datasets/Time-RA/RATs40K) are fully open-sourced to facilitate future research.
@article{arxiv.2507.15066,
title = {Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback},
author = {Yiyuan Yang and Zichuan Liu and Lei Song and Kai Ying and Zhiguang Wang and Tom Bamford and Svitlana Vyetrenko and Jiang Bian and Qingsong Wen},
journal= {arXiv preprint arXiv:2507.15066},
year = {2026}
}
Comments
ACL 2026 Findings. 27 pages, 11 figures, 15 tables. Code and dataset are publicly available