[2603.04951] Retrieval-Augmented Generation with Covariate Time Series

Computer Science > Artificial Intelligence arXiv:2603.04951 (cs) [Submitted on 5 Mar 2026] Title:Retrieval-Augmented Generation with Covariate Time Series Authors:Kenny Ye Liang, Zhongyi Pei, Huan Zhang, Yuhui Liu, Shaoxu Song, Jianmin Wang View a PDF of the paper titled Retrieval-Augmented Generation with Covariate Time Series, by Kenny Ye Liang and 5 other authors View PDF HTML (experimental) Abstract:While RAG has greatly enhanced LLMs, extending this paradigm to Time-Series Foundation Models (TSFMs) remains a challenge. This is exemplified in the Predictive Maintenance of the Pressure Regulating and Shut-Off Valve (PRSOV), a high-stakes industrial scenario characterized by (1) data scarcity, (2) short transient sequences, and (3) covariate coupled dynamics. Unfortunately, existing time-series RAG approaches predominantly rely on generated static vector embeddings and learnable context augmenters, which may fail to distinguish similar regimes in such scarce, transient, and covariate coupled scenarios. To address these limitations, we propose RAG4CTS, a regime-aware, training-free RAG framework for Covariate Time-Series. Specifically, we construct a hierarchal time-series native knowledge base to enable lossless storage and physics-informed retrieval of raw historical regimes. We design a two-stage bi-weighted retrieval mechanism that aligns historical trends through point-wise and multivariate similarities. For context augmentation, we introduce an agent-driven strategy...