# Model-agnostic Retrieval-Augmented Extended Forecasting for time series

arXiv: https://arxiv.org/abs/2608.14054 · HTML: https://mlsanity.com/paper/2608.14054/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Time series and agricultural RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 22 of its 25 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Placed in

- Retrieval-augmented generation / [Time series and agricultural RAG](https://mlsanity.com/rag/time-series-and-agricultural-rag/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting](https://mlsanity.com/paper/2310.09751/) (2023)
- [ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data](https://mlsanity.com/paper/2412.11376/) (2024)
- [Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts](https://mlsanity.com/paper/2410.10469/) (2024)
- [UniTS: A Unified Multi-Task Time Series Model](https://mlsanity.com/paper/2403.00131/) (2024)
- [Retrieval Augmented Time Series Forecasting](https://mlsanity.com/paper/2411.08249/) (2024)
- [TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster](https://mlsanity.com/paper/2503.07649/) (2025)
- [Retrieval-Augmented Diffusion Models for Time Series Forecasting](https://mlsanity.com/paper/2410.18712/) (2024)
- [Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2405.02358/) (2024)
- [TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting](https://mlsanity.com/paper/2412.20810/) (2024)
- [Retrieval-augmented Large Language Models for Financial Time Series Forecasting](https://mlsanity.com/paper/2502.05878/) (2025)
- [Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction](https://mlsanity.com/paper/2402.07570/) (2024)

## Abstract (arXiv)

Time series forecasting with pretrained foundation models has demonstrated strong zero-shot capabilities. However, achieving optimal performance on time series with short or negligible historical data in domain-specific applications typically requires adaptation via either fine-tuning or RAG. While fine-tuning is effective, it incurs substantial computational costs. This work explores RAG within univariate time series (Retrieval Augmented Generation) as a more efficient alternative, in particular RAF (Retrieval Augmented Forecasting), and introduces RAEF (Retrieval-Augmented Extended Forecasting), a model-agnostic method built upon RAF. RAEF incorporates key refinements to the retrieval and aggregation mechanisms: (1) direct retrieval in input-space rather than embedding-space, reducing inference overhead, and (2) concatenation-based aggregation that preserves temporal structure instead of averaging. Empirical evaluation across multiple benchmark datasets demonstrates that RAEF outperforms RAF in both accuracy and inference overhead. Furthermore, comprehensive comparisons with zero-shot and fine-tuned foundation models show that RAEF achieves competitive or superior performance to fine-tuning while avoiding its computational burden, establishing it as a practical and scalable approach for domain adaptation in time series forecasting.