Model-agnostic Retrieval-Augmented Extended Forecasting for time series

Excerpt

arXiv:2608.14054v1 Announce Type: new Abstract: 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 Generatio