mlsanityData to 7 Oct 2026

TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation

arXiv 2412.16643 ↗First posted 21 Dec 2024cs.AIcited by 18

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

Abstract (arXiv)

Although the rise of large language models (LLMs) has introduced new opportunities for time series forecasting, existing LLM-based solutions require excessive training and exhibit limited transferability. In view of these challenges, we propose TimeRAG, a framework that incorporates Retrieval-Augmented Generation (RAG) into time series forecasting LLMs, which constructs a time series knowledge base from historical sequences, retrieves reference sequences from the knowledge base that exhibit similar patterns to the query sequence measured by Dynamic Time Warping (DTW), and combines these reference sequences and the prediction query as a textual prompt to the time series forecasting LLM. Experiments on datasets from various domains show that the integration of RAG improved the prediction accuracy of the original model by 2.97% on average.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Time series and agricultural RAG, one of 15 directions in Retrieval-augmented generation. Builds on 21 of its 30 references that are in the map. First posted on arXiv 21 Dec 2024.

Builds on

21 of 30 references.

References · 21

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  4. 2020Reformer: The Efficient Transformercited by 1,658
  5. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  6. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  7. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  8. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  9. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  10. 2024Chronos: Learning the Language of Time Seriescited by 712
  11. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  12. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
9 more
  1. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  2. 2021AutoFormer: Searching Transformers for Visual Recognitioncited by 186
  3. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 170
  4. 2022FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecastingcited by 147
  5. 2023TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecastingcited by 136
  6. 2024Empowering Time Series Analysis with Large Language Models: A Surveycited by 60
  7. 2024LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Promptingcited by 56
  8. 2023LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Versioncited by 49
  9. 2022Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Databasecited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 5.

18 papers.

Sort:

By area:

  1. 2025TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecastercited by 36
  2. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  3. 2025Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Seriescited by 16
  4. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 15
  5. 2025Retrieval-augmented Large Language Models for Financial Time Series Forecastingcited by 12
  6. 2025BEDTime: A Unified Benchmark for Automatically Describing Time Seriescited by 11
  7. 2025TimeHF: Billion-Scale Time Series Models Guided by Human Feedbackcited by 10
  8. 2025Multimodal Conditioned Diffusive Time Series Forecastingcited by 8
  9. 2025TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrievalcited by 5
  10. 2025Right Answer at the Right Time - Temporal Retrieval-Augmented Generation via Graph Summarizationcited by 3
  11. 2025TimeSense:Making Large Language Models Proficient in Time-Series Analysiscited by 3
  12. 2025Large Language models for Time Series Analysis: Techniques, Applications, and Challengescited by 2
6 more
  1. 2026Enhancing Multivariate Time Series Forecasting with Global Temporal Retrievalcited by 2
  2. 2026Retrieval-Augmented Generation with Covariate Time Seriescited by 1
  3. 2025STRATA-TS: Selective Knowledge Transfer for Urban Time Series Forecasting with Retrieval-Guided Reasoningcited by 0
  4. 2026Enhancing few-shot time series forecasting with LLM-guided diffusioncited by 0
  5. 2026Align-RAG: Alignment Is All You Need for TSFM In-Context Learningcited by 0
  6. 2026JudgeCast: Time Series Forecasting with Experience-Informed Covariate Judgementscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026TS-RAG: Retrieval Augmented Generation for Time Series Forecasting
  2. 2024Retrieval Augmented Time Series Forecasting
  3. 2026Semantics-Enhanced Retrieval-Augmented Time Series Forecasting
  4. 2026Rethinking the Role of LLMs in Time Series Forecasting
  5. 2025Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMs
  6. 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
  7. 2024TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting
  8. 2024A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting