Metraipolis › archive › dc_f6bfd74aeae1
LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications — arXiv:2608.23058
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23058
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:41:48.699Z
- SHA-256 of the archived text
07f0399a038eabbd5f598abf360d7c8af3007b96bb0af47beaa312ae4aa6771b- Stable URL of this page
https://metraipolis.com/documento/dc_f6bfd74aeae1
How to cite
LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications — arXiv:2608.23058 — arXiv (en), https://arxiv.org/abs/2608.23058 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f6bfd74aeae1 (Metraipolis archive dc_f6bfd74aeae1, sha256 07f0399a038eabbd5f598abf360d7c8af3007b96bb0af47beaa312ae4aa6771b)
BibTeX
@misc{dcf6bfd74aeae1,
title = {LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications — arXiv:2608.23058},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23058},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f6bfd74aeae1; sha256 07f0399a038eabbd5f598abf360d7c8af3007b96bb0af47beaa312ae4aa6771b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23058. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) now support forecasting systems that combine language-based reasoning with temporal data, evidence retrieval, external tools, and iterative prediction. We investigate LLM-based forecasting agents, meaning systems in which a language model contributes to a scored prediction about a future or currently unobserved target. We organize architectures into three groups. Standalone LLM workflows operate on encoded time series or event context. Tool- and retrieval-augmented agents incorporate external evidence. Hybrid systems pair LLMs with statistical or foundation models. We then review training methods and evaluation protocols. We examine negative as well as positive evidence, including sensitivity to small input perturbations, ablations in which the LLM component does not improve accuracy, and benchmark gains that may reflect contamination instead of temporal reasoning. We cover applications in finance, weather, health, energy, and operations, and we summarize the benchmarks and datasets used for evaluation. The evidence indicates that measurement is a central limitation. Future work requires calibration under distribution shift, contamination-resistant live evaluation, explicit reporting of cost and accuracy together, and methods for handling feedback between deployed forecasts and the outcomes being forecast. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.23058 — 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 2026-10-18T07:37:52.763Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).