Metraipolis › archive › dc_96fb74efeed9

EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution — arXiv:2610.04517

Source
arXiv
Original
https://arxiv.org/abs/2610.04517
License (as archived)
CC0-1.0
Archived
2026-10-06T05:24:36.885Z
SHA-256 of the archived text
7af280de516ddc7360ffa07a93ac34d98a60a6c3d5db3cbff07d001e98c077d5
Stable URL of this page
https://metraipolis.com/documento/dc_96fb74efeed9

How to cite

EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution — arXiv:2610.04517 — arXiv, https://arxiv.org/abs/2610.04517 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96fb74efeed9 (Metraipolis archive dc_96fb74efeed9, sha256 7af280de516ddc7360ffa07a93ac34d98a60a6c3d5db3cbff07d001e98c077d5)
BibTeX
@misc{dc96fb74efeed9,
  title = {EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution — arXiv:2610.04517},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04517},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96fb74efeed9; sha256 7af280de516ddc7360ffa07a93ac34d98a60a6c3d5db3cbff07d001e98c077d5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04517. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep time-series forecasting models have rapidly diversified, yet adapting them to a specific task still requires extensive expert effort in model selection, mechanism diagnosis, architecture design, implementation, and evaluation. Existing AutoML methods are constrained by predefined search spaces, while general-purpose LLM research agents lack reliable control over experimental protocols and model promotion. We introduce EvoCast, a fully autonomous research-agent system for iterative forecasting architecture evolution. EvoCast first establishes and diagnoses a task-specific baseline through executed mechanism ablations, then generates evidence-grounded research directions from dataset characteristics, diagnostic results, prior rounds, and failure records. Its central design, cognition-authority separation, assigns open-ended hypothesis generation and code implementation to LLM agents, while deterministic program authorities control source-edit boundaries, canonical evaluation, and promotion decisions. Experimental outcomes are accumulated as evidence to guide subsequent rounds. Results show that EvoCast completes complex architecture modifications with higher implementation success and lower agent-side token/time cost, and develops task-specific architectures that outperform selected baselines, strong forecasting models, and agent baselines in three real-world forecasting cases. The code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.04517 — 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 2026-10-06T05:24:05.482Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).