mlsanityData to 14 Oct 2026

LLM Agents for Time-Series: A Survey

arXiv 2608.26226 ↗First posted 26 Aug 2026cs.AIcited by 1

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

Abstract (arXiv)

LLM-based agents are increasingly being developed for time-series problems, but their design choices vary substantially across task settings. This survey adopts a problem-driven taxonomy that organizes these systems by the time-series problems they address rather than by isolated technical components. We group existing systems into four categories: forecasting and reasoning, augmentation and synthesis, anomaly detection and diagnosis, and decision support. Within each category, we examine how task requirements shape agent architecture, tool use, and memory design. We further summarize representative datasets and environments, and compare reported model performance under shared or closely related settings. Overall, this survey offers a task-oriented guide to designing LLM-based agents for time-series problems and identifies open gaps for future work.

Key facts. Cited by 1 paper 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 77 of its 131 references that are in the map. First posted on arXiv 26 Aug 2026.

Builds on

77 of 131 references.

Closest ancestors · 16

Same direction, newest first

  1. 2026Nexus : An Agentic Framework for Time Series Forecasting14 May
  2. 2026TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks5 Feb
  3. 2025ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination10 Oct
  4. 2025Training-Free Time Series Classification via In-Context Reasoning with LLM Agents7 Oct
  5. 2025StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?2 Oct
  6. 2025GridMind: LLMs-Powered Agents for Power System Analysis and Operations2 Sep
  7. 2025FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series24 Aug
  8. 2025Grid-Agent: An LLM-Powered Multi-Agent System for Power Grid Control7 Aug
  9. 2025Empowering Time Series Forecasting with LLM-Agents6 Aug
  10. 2025ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents6 Aug
  11. 2025TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents19 May
  12. 2025TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents17 Feb
4 more
  1. 2024TradingAgents: Multi-Agents LLM Financial Trading Framework28 Dec
  2. 2024TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis5 Oct
  3. 2024MIRAI: Evaluating LLM Agents for Event Forecasting1 Jul
  4. 2023FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design23 Nov

Other references · 61

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  5. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  6. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  8. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  9. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
  10. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  11. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
  12. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
38 more
  1. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  2. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  3. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  4. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 500
  5. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 471
  6. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  7. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  8. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 226
  9. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 224
  10. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 212
  11. 2020A review on outlier/anomaly detection in time series datacited by 189
  12. 2019Time-Series Anomaly Detection Service at Microsoftcited by 165
  13. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 151
  14. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 149
  15. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 138
  16. 2024A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalistcited by 137
  17. 2023LargeST: A Benchmark Dataset for Large-Scale Traffic Forecastingcited by 118
  18. 2024Large Language Models for Time Series: A Surveycited by 114
  19. 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 104
  20. 2019sktime: A Unified Interface for Machine Learning with Time Seriescited by 102
  21. 2015Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmarkcited by 88
  22. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 83
  23. 2023LLMLight: Large Language Models as Traffic Signal Control Agentscited by 73
  24. 2024Empowering Time Series Analysis with Large Language Models: A Surveycited by 60
  25. 2024LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Promptingcited by 59
  26. 2021Learning to run a Power Network Challenge: a Retrospective Analysiscited by 55
  27. 2024HARGPT: Are LLMs Zero-Shot Human Activity Recognizers?cited by 54
  28. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 54
  29. 2023TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learningcited by 52
  30. 2024TimeSeriesExam: A time series understanding examcited by 49
  31. 2025TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loopcited by 39
  32. 2023Open-TI: Open Traffic Intelligence with Augmented Language Modelcited by 38
  33. 2024Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signalscited by 32
  34. 2024UniMTS: Unified Pre-training for Motion Time Seriescited by 26
  35. 2024Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspectivecited by 24
  36. 2024Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotationcited by 21
  37. 2025Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Modelscited by 19
  38. 2025AgentFM: Role-Aware Failure Management for Distributed Databases with LLM-Driven Multi-Agentscited by 19

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026AnyJev Technical Reportcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications
  2. 2026TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning
  3. 2025TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis
  4. 2025When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
  5. 2026Bridging the Last Mile of Time Series Forecasting with LLM Agents
  6. 2026Harnessing Generalist Agents for Contextualized Time Series
  7. 2026EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution
  8. 2026TimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models