{"ID":2876557,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.00616","arxiv_id":"2509.00616","title":"TimeCopilot","abstract":"We introduce TimeCopilot, the first open-source agentic framework for forecasting that combines multiple Time Series Foundation Models (TSFMs) with Large Language Models (LLMs) through a single unified API. TimeCopilot automates the forecasting pipeline: feature analysis, model selection, cross-validation, and forecast generation, while providing natural language explanations and supporting direct queries about the future. The framework is LLM-agnostic, compatible with both commercial and open-source models, and supports ensembles across diverse forecasting families. Results on the large-scale GIFT-Eval benchmark show that TimeCopilot achieves state-of-the-art probabilistic forecasting performance at low cost. Our framework provides a practical foundation for reproducible, explainable, and accessible agentic forecasting systems.","short_abstract":"We introduce TimeCopilot, the first open-source agentic framework for forecasting that combines multiple Time Series Foundation Models (TSFMs) with Large Language Models (LLMs) through a single unified API. TimeCopilot automates the forecasting pipeline: feature analysis, model selection, cross-validation, and forecast...","url_abs":"https://arxiv.org/abs/2509.00616","url_pdf":"https://arxiv.org/pdf/2509.00616v3","authors":"[\"Azul Garza\",\"Renée Rosillo\"]","published":"2025-08-30T21:48:51Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}