mlsanityData to 14 Oct 2026

Retrieval-Augmented Generation with Covariate Time Series

arXiv 2603.04951 ↗First posted 5 Mar 2026cs.AIcited by 1

On the map: Retrieval-augmented generation → Time series and agricultural RAG

Abstract (arXiv)

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 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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Time series and agricultural RAG, one of 15 directions in Retrieval-augmented generation. Builds on 23 of its 44 references that are in the map. First posted on arXiv 5 Mar 2026.

Builds on

23 of 44 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster6 Mar
  2. 2024TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting30 Dec
  3. 2024TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation21 Dec

Other references · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  6. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  8. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  9. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  10. 2024Chronos: Learning the Language of Time Seriescited by 759
  11. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  12. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
8 more
  1. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 500
  2. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 346
  3. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 208
  4. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 197
  5. 2025Chronos-2: From Univariate to Universal Forecastingcited by 194
  6. 2025Sundial: A Family of Highly Capable Time Series Foundation Modelscited by 180
  7. 2024Timer-XL: Long-Context Transformers for Unified Time Series Forecastingcited by 87
  8. 2024A Survey of Deep Learning and Foundation Models for Time Series Forecastingcited by 33

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Post-Training in Time Series Foundation Models: A Unifying Frameworkcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2024Retrieval Augmented Time Series Forecasting
  2. 2024Agentic Retrieval-Augmented Generation for Time Series Analysis
  3. 2026Stationarity-Aware Retrieval-Augmented Time Series Forecasting
  4. 2026Semantics-Enhanced Retrieval-Augmented Time Series Forecasting
  5. 2026TS-RAG: Retrieval Augmented Generation for Time Series Forecasting
  6. 2026Align-RAG: Alignment Is All You Need for TSFM In-Context Learning
  7. 2026Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting
  8. 2026Model-agnostic Retrieval-Augmented Extended Forecasting for time series