mlsanityData to 14 Oct 2026

Empowering Time Series Forecasting with LLM-Agents

arXiv 2508.04231 ↗First posted 6 Aug 2025cs.LG cs.AIcited by 9

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

Abstract (arXiv)

Large Language Model (LLM) powered agents have emerged as effective planners for Automated Machine Learning (AutoML) systems. While most existing AutoML approaches focus on automating feature engineering and model architecture search, recent studies in time series forecasting suggest that lightweight models can often achieve state-of-the-art performance. This observation led us to explore improving data quality, rather than model architecture, as a potentially fruitful direction for AutoML on time series data. We propose DCATS, a Data-Centric Agent for Time Series. DCATS leverages metadata accompanying time series to clean data while optimizing forecasting performance. We evaluated DCATS using four time series forecasting models on a large-scale traffic volume forecasting dataset. Results demonstrate that DCATS achieves an average 6% error reduction across all tested models and time horizons, highlighting the potential of data-centric approaches in AutoML for time series forecasting.

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 21 of its 29 references that are in the map. First posted on arXiv 6 Aug 2025.

Builds on

21 of 29 references.

References · 21

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  3. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  4. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  5. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
  6. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  7. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  8. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringcited by 469
  9. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 366
  10. 2021Monash Time Series Forecasting Archivecited by 267
  11. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
  12. 2023Data-centric Artificial Intelligence: A Surveycited by 203
9 more
  1. 2020Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learningcited by 174
  2. 2023LargeST: A Benchmark Dataset for Large-Scale Traffic Forecastingcited by 118
  3. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 107
  4. 2024MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generationcited by 44
  5. 2024A Survey of Deep Learning and Foundation Models for Time Series Forecastingcited by 33
  6. 2023Toward a Foundation Model for Time Series Datacited by 28
  7. 2023Visual Analytics For Machine Learning: A Data Perspective Surveycited by 25
  8. 2024RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Datacited by 17
  9. 2024Matrix Profile for Anomaly Detection on Multidimensional Time Seriescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025A Survey of Reasoning and Agentic Systems in Time Series with Large Language Modelscited by 21
  2. 2026TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Taskscited by 17
  3. 2025TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understandingcited by 3
  4. 2025TiCT: A Synthetically Pre-Trained Foundation Model for Time Series Classificationcited by 3
  5. 2026Bridging the Last Mile of Time Series Forecasting with LLM Agentscited by 3
  6. 2026TimeClaw: A Time-Series AI Agent with Exploratory Execution Learningcited by 2
  7. 2026LLM Agents for Time-Series: A Surveycited by 1
  8. 2026A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelinescited by 0
  9. 2026Agent-Based Post-Hoc Correction of Agricultural Yield Forecastscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications
  2. 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
  3. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
  4. 2025Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMs
  5. 2026Rethinking the Role of LLMs in Time Series Forecasting
  6. 2025TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis
  7. 2025Efficient Model Selection for Time Series Forecasting via LLMs
  8. 2025TimeCopilot