# TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis

arXiv: https://arxiv.org/abs/2510.01538 · HTML: https://mlsanity.com/paper/2510.01538/

## Key facts

- Cited by 22 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 28 of its 51 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 28 of 28)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2310.08278/) (2023)
- [Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs](https://mlsanity.com/paper/2305.16339/) (2023)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling](https://mlsanity.com/paper/2309.12659/) (2023)
- [GluonTS: Probabilistic Time Series Models in Python](https://mlsanity.com/paper/1906.05264/) (2019)
- [A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series](https://mlsanity.com/paper/2012.00168/) (2020)
- [Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs](https://mlsanity.com/paper/2503.10084/) (2025)
- [SaDI: A Self-adaptive Decomposed Interpretable Framework for Electric Load Forecasting under Extreme Events](https://mlsanity.com/paper/2306.08299/) (2023)
- [Cross-Modal Consistency in Multimodal Large Language Models](https://mlsanity.com/paper/2411.09273/) (2024)
- [Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series](https://mlsanity.com/paper/2506.10412/) (2025)
- [A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization](https://mlsanity.com/paper/2205.14522/) (2022)
- [Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing](https://mlsanity.com/paper/2502.20592/) (2025)
- [Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting](https://mlsanity.com/paper/2505.18442/) (2025)
- [Cherry-Picking in Time Series Forecasting: How to Select Datasets to Make Your Model Shine](https://mlsanity.com/paper/2412.14435/) (2024)
- [QuantHarness: Price-Driven Multi-Agent LLMs for High-Frequency Trading](https://mlsanity.com/paper/2509.09995/) (2025)
- [Integrating Traditional Technical Analysis with AI: A Multi-Agent LLM-Based Approach to Stock Market Forecasting](https://mlsanity.com/paper/2506.16813/) (2025)
- [Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization](https://mlsanity.com/paper/2504.14858/) (2025)

## Built on by (most cited first, 22 of 22)

- [Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling](https://mlsanity.com/paper/2603.04791/) (2026)
- [TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation](https://mlsanity.com/paper/2601.13653/) (2026)
- [TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering](https://mlsanity.com/paper/2510.07432/) (2025)
- [Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting](https://mlsanity.com/paper/2602.01776/) (2026)
- [Nexus : An Agentic Framework for Time Series Forecasting](https://mlsanity.com/paper/2605.14389/) (2026)
- [When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning](https://mlsanity.com/paper/2605.03314/) (2026)
- [Position: Universal Time Series Foundation Models Rest on a Category Error](https://mlsanity.com/paper/2602.05287/) (2026)
- [The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination](https://mlsanity.com/paper/2601.08237/) (2026)
- [Bridging the Last Mile of Time Series Forecasting with LLM Agents](https://mlsanity.com/paper/2606.02497/) (2026)
- [Position: The Inevitable End of One-Architecture-Fits-All-Domains in Time Series Forecasting](https://mlsanity.com/paper/2602.01736/) (2026)
- [CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting](https://mlsanity.com/paper/2604.27840/) (2026)
- [TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning](https://mlsanity.com/paper/2605.10038/) (2026)
- [Heterogeneous Scientific Foundation Model Collaboration](https://mlsanity.com/paper/2604.27351/) (2026)
- [TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning](https://mlsanity.com/paper/2606.03629/) (2026)
- [Towards Verifiable Agentic Data Science: Solving Irregular TSQA Via Tool-Grounded Reasoning](https://mlsanity.com/paper/2606.15107/) (2026)
- [CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting](https://mlsanity.com/paper/2608.03031/) (2026)
- [Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models](https://mlsanity.com/paper/2512.20954/) (2025)
- [When Text and Numbers Disagree: Evidence Arbitration in Large Language Models](https://mlsanity.com/paper/2608.20116/) (2026)
- [When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models](https://mlsanity.com/paper/2608.30395/) (2026)
- [Memory in Deep Time-Series Models](https://mlsanity.com/paper/2609.06006/) (2026)
- [TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent](https://mlsanity.com/paper/2609.27277/) (2026)
- [World2TS: Real-World Event Context for Time-Series Forecasting](https://mlsanity.com/paper/2610.14861/) (2026)

## Abstract (arXiv)

Time series forecasting is central to decision-making in domains as diverse as energy, finance, climate, and public health. In practice, forecasters face thousands of short, noisy series that vary in frequency, quality, and horizon, where the dominant cost lies not in model fitting, but in the labor-intensive preprocessing, validation, and ensembling required to obtain reliable predictions. Prevailing statistical and deep learning models are tailored to specific datasets or domains and generalize poorly. A general, domain-agnostic framework that minimizes human intervention is urgently in demand. In this paper, we introduce TimeSeriesScientist (TSci), the first LLM-driven agentic framework for general time series forecasting. The framework comprises four specialized agents: Curator performs LLM-guided diagnostics augmented by external tools that reason over data statistics to choose targeted preprocessing; Planner narrows the hypothesis space of model choice by leveraging multi-modal diagnostics and self-planning over the input; Forecaster performs model fitting and validation and, based on the results, adaptively selects the best model configuration as well as ensemble strategy to make final predictions; and Reporter synthesizes the whole process into a comprehensive, transparent report. With transparent natural-language rationales and comprehensive reports, TSci transforms the forecasting workflow into a white-box system that is both interpretable and extensible across tasks. Empirical results on eight established benchmarks demonstrate that TSci consistently outperforms both statistical and LLM-based baselines, reducing forecast error by an average of 10.4% and 38.2%, respectively. Moreover, TSci produces a clear and rigorous report that makes the forecasting workflow more transparent and interpretable.