Metraipolis › archive › dc_bca5bc9ee1ac

Model-agnostic Retrieval-Augmented Extended Forecasting for time series — arXiv:2608.14054

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14054
License (as archived)
CC0-1.0
Archived
2026-10-19T02:30:32.432Z
SHA-256 of the archived text
fdfbe74151dd3897285ebf063d956789c7e5369689055544f653da813c046b50
Stable URL of this page
https://metraipolis.com/documento/dc_bca5bc9ee1ac

How to cite

Model-agnostic Retrieval-Augmented Extended Forecasting for time series — arXiv:2608.14054 — arXiv (en), https://arxiv.org/abs/2608.14054 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bca5bc9ee1ac (Metraipolis archive dc_bca5bc9ee1ac, sha256 fdfbe74151dd3897285ebf063d956789c7e5369689055544f653da813c046b50)
BibTeX
@misc{dcbca5bc9ee1ac,
  title = {Model-agnostic Retrieval-Augmented Extended Forecasting for time series — arXiv:2608.14054},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14054},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bca5bc9ee1ac; sha256 fdfbe74151dd3897285ebf063d956789c7e5369689055544f653da813c046b50},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14054. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.14054 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T02:26:17.788Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).