Metraipolis › archive › dc_b7fe1a03e7ef

Compositional Spectral Prompts for LLM-based Online Time Series Forecasting — arXiv:2609.02093

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02093
License (as archived)
CC0-1.0
Archived
2026-10-17T04:59:24.005Z
SHA-256 of the archived text
23d6fa9e6d95709395f7d1b3c85a6b1e445e665c1c65333c08408d2eb9f30e8b
Stable URL of this page
https://metraipolis.com/documento/dc_b7fe1a03e7ef

How to cite

Compositional Spectral Prompts for LLM-based Online Time Series Forecasting — arXiv:2609.02093 — arXiv (en), https://arxiv.org/abs/2609.02093 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b7fe1a03e7ef (Metraipolis archive dc_b7fe1a03e7ef, sha256 23d6fa9e6d95709395f7d1b3c85a6b1e445e665c1c65333c08408d2eb9f30e8b)
BibTeX
@misc{dcb7fe1a03e7ef,
  title = {Compositional Spectral Prompts for LLM-based Online Time Series Forecasting — arXiv:2609.02093},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02093},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b7fe1a03e7ef; sha256 23d6fa9e6d95709395f7d1b3c85a6b1e445e665c1c65333c08408d2eb9f30e8b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02093. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

To address the sequential and evolving nature of time series, the Online Time Series Forecasting (OTSF) task has been extensively studied in multiple domains. Existing research focuses on adapting to non-stationary environments by employing memory buffer-based retrieval strategies. However, we observe that such frameworks struggle with long-term adaptation and fail to generalize to unseen patterns. To this end, we introduce CoSPOT, an LLM-based online time series forecasting framework that leverages a pre-trained LLM as the backbone online forecaster, motivated by its strong few-shot capabilities. For efficient online adaptation, CoSPOT keeps the LLM frozen and employs compositional spectral prompts grounded in frequency-domain bases to guide the model with the overall distribution of the input, thereby substantially reducing the number of parameters updated during the online phase. Specifically, CoSPOT decomposes time series into frequency bases and composes the corresponding spectral basis prompts according to their amplitudes, allowing unseen patterns to be represented as new combinations of learned basis prompts. Our extensive experiments on real-world datasets demonstrate the superiority and practicality of CoSPOT across challenging online scenarios, including extended online phases and cross-dataset settings with substantial distribution shifts. Our code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.02093 — 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 2026-10-17T04:09:43.306Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).