mlsanityData to 14 Oct 2026

TimeCopilot

arXiv 2509.00616 ↗First posted 30 Aug 2025cs.LG cs.AI cs.HCcited by 9

On the map: LLM agents and tool use → Financial trading and forecasting agents

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 23 of its 39 references that are in the map. First posted on arXiv 30 Aug 2025.

Builds on

23 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents19 May

Other references · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  4. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  5. 2023A decoder-only foundation model for time-series forecastingcited by 692
  6. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  7. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  8. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 287
  9. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 212
  10. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 208
  11. 2025Sundial: A Family of Highly Capable Time Series Foundation Modelscited by 180
  12. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 178
10 more
  1. 2021Pretrained Transformers as Universal Computation Enginescited by 162
  2. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 127
  3. 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learningcited by 120
  4. 2024Timer-XL: Long-Context Transformers for Unified Time Series Forecastingcited by 87
  5. 2024Context is Key: A Benchmark for Forecasting with Essential Textual Informationcited by 87
  6. 2020Meta-learning framework with applications to zero-shot time-series forecastingcited by 70
  7. 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Modelscited by 65
  8. 2025From Tables to Time: Extending TabPFN-v2 to Time Series Forecastingcited by 60
  9. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  10. 2024Toto: Time Series Optimized Transformer for Observabilitycited by 48

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 8.

9 papers.

  1. 2026Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scalingcited by 28
  2. 2026Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecastingcited by 9
  3. 2025Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Modelscited by 7
  4. 2026Nexus : An Agentic Framework for Time Series Forecastingcited by 6
  5. 2026TimeRouter: Efficient and Adaptive Routing of Time-Series Foundation Modelscited by 2
  6. 2026TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoningcited by 1
  7. 2026TimeEvo: Failure-Driven Self-Evolution of a Time Series Agentcited by 0
  8. 2026Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMscited by 0
  9. 2026TimeNet: An Extensible Unified Data Infrastructure for Next-Generation Temporal Foundation Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning
  2. 2025Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting
  3. 2026Agentic Time Machine as an Infrastructure for Future-Event Forecasting
  4. 2026TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning
  5. 2026LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications
  6. 2026OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning
  7. 2026CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting
  8. 2025AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting