Update README.md

README.md

@@ -1,3 +1,48 @@
 ---
-license: apache-2.0
+library_name: pytorch
+tags:
+  - time-series
+  - time-series-forecasting
+  - foundation-models
+  - retrieval-augmented-generation
+  - rag
 ---
+
+# RAEF
+
+**Retrieval-Augmented Extended Forecasting**
+
+Official implementation of:
+
+**Model-Agnostic Retrieval-Augmented Extended Forecasting for Time Series**
+
+📄 Paper:
+https://arxiv.org/abs/2608.14054
+
+💻 GitHub:
+https://github.com/jpvilla1990/raef
+
+## Overview
+
+RAEF is a model-agnostic retrieval-augmented inference framework
+for time-series foundation models.
+
+The method retrieves relevant historical time series directly
+in input space and uses concatenation-based aggregation to
+extend the forecasting context.
+
+## Code
+
+The complete source code and experiments are available on GitHub:
+
+https://github.com/jpvilla1990/raef
+
+## Citation
+
+```bibtex
+@article{villa2026modelagnostic,
+  title={Model-Agnostic Retrieval-Augmented Extended Forecasting for time series},
+  author={Villa Serna, Juan Pablo and Asthana, Rohan and Belagiannis, Vasileios},
+  journal={arXiv preprint arXiv:2608.14054},
+  year={2026}
+}