mlsanityData to 7 Oct 2026

TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation

arXiv 2601.13653 ↗First posted 20 Jan 2026cs.LGcited by 25

On the map: LLM reasoning → Time series reasoning

also in 1 more
Abstract (arXiv)

Time series data widely exist in real-world cyber-physical systems. Though analyzing and interpreting them contributes to significant values, e.g, disaster prediction and financial risk control, current workflows mainly rely on human data scientists, which requires significant labor costs and lacks automation. To tackle this, we introduce TimeART, a framework fusing the analytical capability of strong out-of-the-box tools and the reasoning capability of Large Language Models (LLMs), which serves as a fully agentic data scientist for Time Series Question Answering (TSQA). To teach the LLM-based Time Series Reasoning Models (TSRMs) strategic tool-use, we also collect a 100k expert trajectory corpus called TimeToolBench. To enhance TSRMs' generalization capability, we then devise a four-stage training strategy, which boosts TSRMs through learning from their own early experiences and self-reflections. Experimentally, we train an 8B TSRM on TimeToolBench and equip it with the TimeART framework, and it achieves consistent state-of-the-art performance on multiple TSQA tasks, which pioneers a novel approach towards agentic time series reasoning.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in Time series reasoning, one of 17 directions in LLM reasoning. Builds on 34 of its 75 references that are in the map. First posted on arXiv 20 Jan 2026.

Builds on

34 of 75 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Training-Free Time Series Classification via In-Context Reasoning with LLM Agents7 Oct
  2. 2025MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering21 Mar
  3. 2024ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning4 Dec

Other references · 31

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2024GPT-4o System Cardcited by 4,467
  5. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  6. 2024DeepSeek-V3 Technical Reportcited by 724
  7. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  8. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  9. 2024Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agentscited by 144
  10. 2025Agent Learning via Early Experiencecited by 79
  11. 2025Time-MQA: Time Series Multi-Task Question Answering with Context Enhancementcited by 74
  12. 2025Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Conceptscited by 61
19 more
  1. 2025A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspectivecited by 58
  2. 2025ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understandingcited by 50
  3. 2024TimeSeriesExam: A time series understanding examcited by 47
  4. 2024Can LLMs Understand Time Series Anomalies?cited by 41
  5. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  6. 2024Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoderscited by 37
  7. 2024WcDT: World-centric Diffusion Transformer for Traffic Scene Generationcited by 31
  8. 2025DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variablescited by 30
  9. 2025Aurora: Towards Universal Generative Multimodal Time Series Forecastingcited by 28
  10. 2025TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysiscited by 18
  11. 2025PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Playcited by 14
  12. 2025A Survey on Mathematical Reasoning and Optimization with Large Language Modelscited by 12
  13. 2025Towards Non-Stationary Time Series Forecasting with Temporal Stabilization and Frequency Differencingcited by 8
  14. 2025ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecastingcited by 7
  15. 2025An Encode-then-Decompose Approach to Unsupervised Time Series Anomaly Detection on Contaminated Training Data--Extended Versioncited by 3
  16. 2025FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecastingcited by 3
  17. 2025Task-Aware Mixture-of-Experts for Time Series Analysiscited by 2
  18. 2025ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecastingcited by 1
  19. 2025Hermes: A Multi-Scale Spatial-Temporal Hypergraph Network for Stock Time Series Forecastingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 25.

25 papers.

Sort:

By area:

  1. 2026Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecastingcited by 9
  2. 2026FinSTaR: Towards Financial Reasoning with Time Series Reasoning Modelscited by 4
  3. 2026KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoningcited by 4
  4. 2026AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoningcited by 3
  5. 2026TimeClaw: A Time-Series AI Agent with Exploratory Execution Learningcited by 2
  6. 2026Harnessing Generalist Agents for Contextualized Time Seriescited by 2
  7. 2026WPBench: A Comprehensive Benchmark for Wind Power Forecastingcited by 2
  8. 2026Multimodal Collaborative Debate for Zero-Shot Time Series Reasoningcited by 1
  9. 2026ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologiescited by 1
  10. 2026From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligencecited by 1
  11. 2026TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoningcited by 1
  12. 2026Towards Verifiable Agentic Data Science: Solving Irregular TSQA Via Tool-Grounded Reasoningcited by 1
13 more
  1. 2026Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoningcited by 0
  2. 2026From Recognition to Understanding: Unlocking Cognitive Time Series Reasoning with LLMscited by 0
  3. 2026CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecastingcited by 0
  4. 2026MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasterscited by 0
  5. 2026T-SMART: Mechanism-Level Attribution for Tool-Augmented Time-Series Question Answeringcited by 0
  6. 2026MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecastingcited by 0
  7. 2026When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecastingcited by 0
  8. 2026TimeEvo: Failure-Driven Self-Evolution of a Time Series Agentcited by 0
  9. 2026Aurora-X: Built for Extreme Time Series Forecastingcited by 0
  10. 2026WorldTS: World Modeling for Multimodal Covariate-aware Time Series Forecastingcited by 0
  11. 2026QiYao-M: Multimodal Time Series Foundation Model with Role-Aware Modeling of Endogenous and Exogenous Modalitiescited by 0
  12. 2026XMatch: Enhancing Covariate-Aware Time Series Forecasting through Tree-Structured Exogenous Matchingcited by 0
  13. 2026Towards Reliable AI Data Scientists: Data Agents with Workflow Harnessescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering
  2. 2026TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning
  3. 2026Thoth: Mid-Training Bridges LLMs to Time Series Understanding
  4. 2026TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering
  5. 2024TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
  6. 2025A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models
  7. 2025When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
  8. 2024Towards Time Series Reasoning with LLMs