Metraipolis › archive › dc_c10bfbd472ca

When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting — arXiv:2609.24862

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.24862
License (as archived): CC0-1.0
Archived: 2026-10-09T07:07:57.002Z
SHA-256 of the archived text: e8def564541e85c4f9247d1be189749ba85dcbfa3fc4a827acca178267783426
Stable URL of this page: https://metraipolis.com/documento/dc_c10bfbd472ca

How to cite

When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting — arXiv:2609.24862 — arXiv (en), https://arxiv.org/abs/2609.24862 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c10bfbd472ca (Metraipolis archive dc_c10bfbd472ca, sha256 e8def564541e85c4f9247d1be189749ba85dcbfa3fc4a827acca178267783426)

BibTeX

@misc{dcc10bfbd472ca,
  title = {When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting — arXiv:2609.24862},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24862},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c10bfbd472ca; sha256 e8def564541e85c4f9247d1be189749ba85dcbfa3fc4a827acca178267783426},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24862. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic time series forecasting concerns systems whose underlying mechanisms evolve, making the relative effectiveness of numerical models, reasoning strategies, and intervention rules inherently time-varying. Consequently, a time series agent must adapt the forecasts it produces and the orchestration policy that determines which components to trust and how to coordinate them. The deployment process naturally provides supervision for this adaptation as forecast horizons elapse and realized targets reveal the effectiveness of earlier decisions. Committing all numerical expert forecasts and candidate agent paths before target observation allows each realized outcome to evaluate the entire alternative set, providing delayed feedback without additional annotation. However, existing time series agents primarily incorporate prior experience through forecast refinement, reflection, or retrieval, without systematically converting realized outcomes into persistent updates to the joint orchestration policy governing later origins. To exploit this delayed feedback systematically, we introduce TimEvolve, a frozen-backbone time series agent that converts each realized outcome into persistent joint updates of expert trust, agent path selection, and intervention strength. A temporally ordered predict, reveal, and update protocol applies this feedback to subsequent forecasts. Experiments across eight Time-MMD domains show that TimEvolve achieves the best average MSE and MAE ranks among fifteen methods and the lowest errors on both metrics in seven domains. These results demonstrate the value of learning forecasting policies from the futures encountered during deployment.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.24862 — 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 2026-10-09T06:58:09.452Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).