TimeCopilot

Azul Garza, Renee Rosillo Garcia

Keywords: time series forecasting, foundation models, large language models, agentic systems, automated forecasting, explainability, reproducibility, open source

TL;DR: TimeCopilot unifies time series foundation models and LLMs in a single agentic framework, automating forecasting pipelines with explanations, queries, and reproducible state-of-the-art results.

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.

Submission Number: 28