Retrieval-Augmented Generation with Covariate Time Series
#Retrieval-Augmented Generation #RAG #covariate time series #forecasting #generative AI #data retrieval #predictive modeling
📌 Key Takeaways
- Retrieval-Augmented Generation (RAG) is being applied to covariate time series data.
- The approach enhances time series forecasting by integrating external information retrieval.
- It aims to improve model accuracy and context-awareness in predictions.
- The method combines generative AI with structured time-dependent variables.
📖 Full Retelling
arXiv:2603.04951v1 Announce Type: new
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 sta
🏷️ Themes
AI Forecasting, Time Series
📚 Related People & Topics
Entity Intersection Graph
Connections for Rag:
🌐
Artificial intelligence
1 shared
Mentioned Entities
Original Source
--> Computer Science > Artificial Intelligence arXiv:2603.04951 [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 Abstract: While RAG has greatly enhanced LLMs, extending this paradigm to Time-Series Foundation Models remains a challenge. This is exemplified in the Predictive Maintenance of the Pressure Regulating and Shut-Off Valve , 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 to dynamically optimize context in a self-supervised manner. Extensive experiments on PRSOV demonstrate that our framework significantly outperforms state-of-the-art baselines in prediction accuracy. The proposed system is deployed in Apache IoTDB within China Southern Airlines. Since deployment, our method has successfully identified one PRSOV fault in two months with zero false alarm. Comments: 12 pages. Preprint Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.04951 [cs.AI] (or arXiv:2603.04951v1 [cs.AI]...
Read full article at source