Metraipolis › archive › dc_eac1855814fa
ReasonCast: Agentic Demand Forecasting with Selective Semantic Reasoning — arXiv:2608.15291
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15291
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:13:33.062Z
- SHA-256 of the archived text
46082ae2fd68ce574e9e349a35fb6039c0a6307579e65e501cafcad254ebe603- Stable URL of this page
https://metraipolis.com/documento/dc_eac1855814fa
How to cite
ReasonCast: Agentic Demand Forecasting with Selective Semantic Reasoning — arXiv:2608.15291 — arXiv (en), https://arxiv.org/abs/2608.15291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eac1855814fa (Metraipolis archive dc_eac1855814fa, sha256 46082ae2fd68ce574e9e349a35fb6039c0a6307579e65e501cafcad254ebe603)
BibTeX
@misc{dceac1855814fa,
title = {ReasonCast: Agentic Demand Forecasting with Selective Semantic Reasoning — arXiv:2608.15291},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15291},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eac1855814fa; sha256 46082ae2fd68ce574e9e349a35fb6039c0a6307579e65e501cafcad254ebe603},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Demand forecasting increasingly requires combining two complementary sources of information: historical sales reveal recurring numerical dynamics, while future promotions, holidays, price changes, and platform interventions provide forward-looking knowledge. Existing text-enhanced forecasting methods often encode such context into generic representations and fuse it uniformly with time-series features, without explicitly distinguishing which semantic effects are forecast-relevant or how they should modify future dynamics. We introduce ReasonCast, a structured semantic intervention framework that translates event knowledge into forecast-specific operations. An agent examines the event context, the no-text forecast, and its uncertainty to determine whether textual reasoning is needed. Rather than injecting free-form text, ReasonCast represents event knowledge through structured fields describing event relevance, demand direction, temporal shape, amplitude, and peak intensity. These fields interact selectively with temporal components of a time-series foundation model. An additive path corrects local trends and temporal shapes, while a multiplicative path captures event-driven level shifts. ReasonCast introduces a forecast-grounded post-training curriculum. Schema SFT establishes semantic fields; semantic-field RL calibrates direction, shape, amplitude, and peak judgments; and forecast-utility RL evaluates semantic interventions through a frozen forecaster, aligning reasoning outputs with marginal forecast improvement. ReasonCast lowers WMAPE by 3.29, 1.25, and 0.47 percentage points on holiday-sensitive categories, mega-sale-sensitive categories, and M5 event windows, respectively. On stable-sales periods, indiscriminate semantic intervention increases WMAPE by 1.68 percentage points, whereas suppressing unnecessary intervention preserves the numerical backbone. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.15291 — 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 2026-10-18T16:29:13.785Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).