TimeCopilot

2025/08/30 by Azul Garza, Garza, Azul, Renée Rosillo +1 · 1 citation
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Forecasting Techniques and Applications #Human-Computer Interaction (cs.HC) #Machine Learning (cs.LG) #Stock Market Forecasting Methods

paper · pdf · doi:10.48550/arxiv.2509.00616

openalex publication_date 2025/08/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
• TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents
• Sundial: A Family of Highly Capable Time Series Foundation Models
• From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting
• Context is Key: A Benchmark for Forecasting with Essential Textual Information
• GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
• Timer-XL: Long-Context Transformers for Unified Time Series Forecasting
• Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
• Large Language Model-Based Agents for Software Engineering: A Survey
• Toto: Time Series Optimized Transformer for Observability
• MOMENT: A Family of Open Time-series Foundation Models
• Unified Training of Universal Time Series Forecasting Transformers
• AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
• Timer: Generative Pre-trained Transformers Are Large Time Series Models
• Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
• A decoder-only foundation model for time-series forecasting
• Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
• A Survey on Time-Series Pre-Trained Models
• Pretrained Transformers as Universal Computation Engines
• Language Models are Few-Shot Learners
• Meta-learning framework with applications to zero-shot time-series forecasting
• Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
• Temporal Fusion Transformers for interpretable multi-horizon time series forecasting
• Forecasting at Scale
• Attention Is All You Need
• Another look at measures of forecast accuracy
• The Combination of Forecasts
• Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
• The M4 Competition: 100,000 time series and 61 forecasting methods

Cited by

• Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models

Related

• TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis
• Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting
• LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
• Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
• Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting