Skip to content

Latest commit

 

History

46 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models

TMLR arXiv GitHub Stars Topic How to Cite

✨ If you find our survey useful, a star ⭐ on GitHub helps others discover it and keeps you updated on future releases.

Overview

Time series reasoning treats time as a first-class axis and integrates intermediate evidence into the answer itself.
This survey organizes the field along two levels:

  • Reasoning Topology — execution structures:

    • Direct reasoning (single step)
    • Linear chain reasoning (sequential intermediate steps)
    • Branch-structured reasoning (exploration, feedback, and aggregation)
  • Primary Objective — the main intent:

    • Traditional time series analysis (forecasting, classification, anomaly detection, segmentation)
    • Explanation and understanding (temporal QA, diagnostics, structure discovery)
    • Causal inference and decision making (counterfactuals, policy evaluation, decision support)
    • Time series generation (simulation, editing, synthesis)

We complement this two-level taxonomy with attribute tags that capture control-flow operators (decomposition, verification, ensembling), execution actors (tool use, agents), information sources (knowledge access, multimodality), and alignment regimes (prompting, supervised finetuning, reinforcement/preference, hybrid).

This repository curates and classifies both research papers and non-research contributions in the field.

  • Research papers are categorized by reasoning topology and primary objective.
  • Non-research papers include datasets & benchmarks (reasoning-first, reasoning-ready, general-purpose TS), as well as surveys, tutorials, and position/vision papers.

The following table presents the unified taxonomy and tags for all research papers we review, while non-research contributions are grouped separately for completeness.

Paper Counts

The distribution of surveyed papers, split into research and non-research categories:

Surveyed papers count: research and non-research

Table of Contents

Abbreviations & Value Definitions

Covers: abbreviations and value definitions for primary objectives, task values, and attribute tags used in the curated research-paper taxonomy tables.

Non-research papers are listed without attribute tags.

Attribute Tag Headers (8 total)

Full Name Abbreviation
Task Decomposition T-Dec
Verification and Critique T-Ver
Ensemble Selection T-Ens
Tool Use T-Tool
Knowledge Access T-Know
Multimodal Inputs T-Multi
Agents T-Agent
LLM Alignment T-Align

Primary Objective Values

Full Name Abbreviation
Traditional Time Series Analysis Trad. TS Anal.
Explanation and Understanding Expl. & Und.
Causal Inference and Decision Making Causal Inf.
Time Series Generation TS Gen.

Task Values

Full Name Abbreviation
Forecasting Forc.
Classification Class.
Anomaly Detection Anom. Det.
Segmentation Segm.
Multiple Tasks Mult. Tasks
Temporal Question Answering Temp. QA
Explanatory Diagnostics Expl. Diagn.
Structure Discovery Struct. Disc.
Autonomous Policy Learning Auto. Policy
Advisory Decision Support Adv. Dec. Supp.
Conditioned Synthesis Cond. Synth.

Attribute Tag Values (Legend)

Tag(s) Values / Meaning
T-Dec, T-Ver, T-Ens, T-Tool, T-Know, T-Multi ✔ = present, empty = absent
T-Agent 0 = no agent, 1 = single agent, M = multiple agents
T-Align P = Prompting, S = Supervised fine-tuning, R = Reinforcement/preference alignment, H = Hybrid

Research Papers for Direct Reasoning

                                        Paper                                         Primary Objective Task T-Dec T-Ver T-Ens T-Tool T-Know T-Multi T-Agent T-Align
Large Language Models Are Zero-Shot Time Series Forecasters [NeurIPS 2023] Trad. TS Anal. Forc. 0 P
Context is Key: A Benchmark for Forecasting with Essential Textual Information [ICML 2025] Trad. TS Anal. Forc. 0 P
DP-GPT4MTS: Dual-Prompt Large Language Model for Textual-Numerical Time Series Forecasting [arXiv 2025] Trad. TS Anal. Forc. 0 S
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting [ICLR 2024] Trad. TS Anal. Forc. 0 S
Rethinking Time Series Forecasting with LLMs via Nearest Neighbor Contrastive Learning [arXiv 2024] Trad. TS Anal. Forc. 0 S
CMLLM: A Novel Cross-Modal Large Language Model for Wind Power Forecasting [Energy Conversion and Management 2025] Trad. TS Anal. Forc. 0 P
Multi-Modal Forecaster: Jointly Predicting Time Series and Textual Data [arXiv 2024] Trad. TS Anal. Forc. 0 S
Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities [SIGKDD Explor. Newsl. 2025] Trad. TS Anal. Forc. 0 P
Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification [arXiv 2024] Trad. TS Anal. Class. 0 S
Multimodal LLMs for Health Grounded in Individual-Specific Data [Machine Learning for Multimodal Healthcare Data 2023] Trad. TS Anal. Class. 0 S
Retrieval-augmented Large Language Models for Financial Time Series Forecasting [arXiv 2025] Trad. TS Anal. Class. 0 S
Can LLMs Understand Time Series Anomalies? [ICLR 2025] Trad. TS Anal. Anom. Det. 0 P
MedTsLLM: Leveraging LLMs for Multimodal Medical Time Series Analysis [arXiv 2024] Trad. TS Anal. Segm. 0 P
ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data [AAAI 2025] Trad. TS Anal. Mult. Tasks 0 S
Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data [arXiv 2025] Expl. & Und. Temp. QA 0 S
ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning [VLDB 2025] Expl. & Und. Temp. QA 0 S
ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset [ICML 2025] Expl. & Und. Temp. QA 0 P
Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement [ACL 2025] Expl. & Und. Temp. QA 0 S
GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images [arXiv 2025] Expl. & Und. Expl. Diagn. 0 S
Time-RA: Towards Time Series Reasoning for Anomaly with LLM Feedback [arXiv 2025] Expl. & Und. Expl. Diagn. 0 S
Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning [ICML 2024] Expl. & Und. Expl. Diagn. 0 P
RealTCD: Temporal Causal Discovery from Interventional Data with Large Language Model [CIKM 2024] Expl. & Und. Struct. Disc. 0 P
GG-LLM: Geometrically Grounding Large Language Models for Zero-shot Human Activity Forecasting in Human-Aware Task Planning [ICRA 2024] Causal Inf. Auto. Policy 0 P

Research Papers for Linear Chain Reasoning

                                        Paper                                         Primary Objective Task T-Dec T-Ver T-Ens T-Tool T-Know T-Multi T-Agent T-Align
Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting [arXiv 2025] Trad. TS Anal. Forc. 0 P
Retrieval Augmented Time Series Forecasting [arXiv 2024] Trad. TS Anal. Forc. 0 S
TimeRAG: Boosting LLM Time Series Forecasting via Retrieval-Augmented Generation [arXiv 2024] Trad. TS Anal. Forc. 0 P
Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs [arXiv 2025] Trad. TS Anal. Forc. 0 H
Temporal Data Meets LLM - Explainable Financial Time Series Forecasting [arXiv 2023] Trad. TS Anal. Forc. 0 S
CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting [arXiv 2026] Trad. TS Anal. Forc. 0 P
TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models [arXiv 2024] Trad. TS Anal. Class. 0 P
A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization [NAACL 2025] Trad. TS Anal. Class. 0 P
ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents [arXiv 2025] Trad. TS Anal. Class. M P
TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning [arXiv 2025] Trad. TS Anal. Class. 0 H
Towards Time-Series Reasoning with LLMs [NeurIPS Workshop on Time Series in the Age of Large Models 2024] Trad. TS Anal. Class. 0 S
REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models [arXiv 2024] Trad. TS Anal. Class. 0 P
Harnessing Vision-Language Models for Time Series Anomaly Detection [arXiv 2025] Trad. TS Anal. Anom. Det. 0 P
Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detection [KDD 2025] Trad. TS Anal. Anom. Det. 0 P
Can LLMs Serve As Time Series Anomaly Detectors? [arXiv 2024] Trad. TS Anal. Anom. Det. 0 S
Large language models can be zero-shot anomaly detectors for time series? [DSAA 2024] Trad. TS Anal. Anom. Det. 0 P
Large-model-based smart agent for time series anomaly detection in power systems [Expert Systems with Applications 2025] Trad. TS Anal. Anom. Det. 1 P
LEMAD: LLM-Empowered Multi-Agent System for Anomaly Detection in Power Grid Services [Electronics 2025] Trad. TS Anal. Anom. Det. M P
A Time Series Multitask Framework Integrating a Large Language Model, Pre-Trained Time Series Model, and Knowledge Graph [arXiv 2025] Trad. TS Anal. Mult. Tasks 0 P
Agentic Retrieval-Augmented Generation for Time Series Analysis [arXiv 2024] Trad. TS Anal. Mult. Tasks M H
Inferring Events from Time Series using Language Models [arXiv 2025] Expl. & Und. Temp. QA 0 H
Large Language Models Can Learn Temporal Reasoning [ACL 2024] Expl. & Und. Temp. QA 0 S
TempoGPT: Enhancing Time Series Reasoning via Quantizing Embedding [arXiv 2025] Expl. & Und. Expl. Diagn. 0 S
Time Series Language Model for Descriptive Caption Generation [arXiv 2025] Expl. & Und. Expl. Diagn. 0 S
Visual Analysis of Time Series Data for Multi-Agent Systems Driven by Large Language Models [SPCNC 2024] Expl. & Und. Expl. Diagn. M P
A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist [KDD 2024] Causal Inf. Auto. Policy 1 P
FINMEM: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design [ICLR Workshop on Large Language Model (LLM) Agents 2024] Causal Inf. Auto. Policy 1 P
Open-TI: Open Traffic Intelligence with Augmented Language Model [International Journal of Machine Learning and Cybernetics 2024] Causal Inf. Auto. Policy M P
SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series [ICLR 2024] Causal Inf. Adv. Dec. Supp. M P
GenG: An LLM-based Generic Time Series Data Generation Approach for Edge Intelligence via Cross-domain Collaboration [INFOCOM Wksps 2024] TS Gen. Cond. Synth. 0 S
Using Gen AI Agents With GAE And VAE To Enhance Resilience Of Us Markets [SSRN 2025] TS Gen. Cond. Synth. 0 P

Research Papers for Branch-Structured Reasoning

                                        Paper                                         Primary Objective Task T-Dec T-Ver T-Ens T-Tool T-Know T-Multi T-Agent T-Align
Can Competition Enhance the Proficiency of Agents Powered by Large Language Models in the Realm of News-driven Time Series Forecasting? [arXiv 2025] Trad. TS Anal. Forc. M S
From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection [NeurIPS 2024] Trad. TS Anal. Forc. M S
Context-Aware Probabilistic Modeling with LLM for Multimodal Time Series Forecasting [arXiv 2025] Trad. TS Anal. Forc. 0 P
Empowering Time Series Forecasting with LLM-Agents [arXiv 2025] Trad. TS Anal. Forc. 1 P
CoLLM: Industrial Large-Small Model Collaboration with Fuzzy Decision-making Agent and Self-Reflection [IEEE Transactions on Fuzzy Systems 2025] Trad. TS Anal. Forc. 0 S
Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop [arXiv 2025] Trad. TS Anal. Forc. M P
CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting [arXiv 2026] Trad. TS Anal. Forc. 1 H
Enhancing LLM Reasoning for Time Series Classification by Tailored Thinking and Fused Decision [arXiv 2025] Trad. TS Anal. Class. 0 P
ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration [WWW 2025] Trad. TS Anal. Class. M P
TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents [AAAI 2025] Trad. TS Anal. Class. M P
AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection [arXiv 2025] Trad. TS Anal. Anom. Det. M P
ARGOS: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models [arXiv 2025] Trad. TS Anal. Anom. Det. 0 P
See it, Think it, Sorted: Large Multimodal Models are Few-shot Time Series Anomaly Analyzers [arXiv 2024] Trad. TS Anal. Anom. Det. 0 P
LLM-TSFD: An industrial time series human-in-the-loop fault diagnosis method based on a large language model [Expert Systems with Applications 2025] Trad. TS Anal. Anom. Det. 1 P
Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis [arXiv 2025] Trad. TS Anal. Mult. Tasks 1 P
MERIT: Multi-Agent Collaboration for Unsupervised Time Series Representation Learning [ACL 2025] Trad. TS Anal. Mult. Tasks M P
Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation [arXiv 2024] Expl. & Und. Expl. Diagn. M P
AgentFM: Role-Aware Failure Management for Distributed Databases with LLM-Driven Multi-Agents [FSE 2025] Expl. & Und. Expl. Diagn. M P
ElliottAgents: A Natural Language-Driven Multi-Agent System for Stock Market Analysis and Prediction [PACLIC 2024] Expl. & Und. Expl. Diagn. M P
Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents [arXiv 2026] Expl. & Und. Expl. Diagn. M P
Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series? [arXiv 2025] Expl. & Und. Struct. Disc. 0 P
FinArena: A Human-Agent Collaboration Framework for Financial Market Analysis and Forecasting [arXiv 2025] Causal Inf. Auto. Policy M P
FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making [NeurIPS 2024] Causal Inf. Auto. Policy M P
TradingAgents: Multi-Agents LLM Financial Trading Framework [AAA Workshop on Multi-Agent AI in the Real World 2025] Causal Inf. Auto. Policy M P
BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling [ICML 2025] TS Gen. Cond. Synth. M P

Non-Research Papers

                                        Paper                                         Type
Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmark [EMNLP 2024] Reasoning-First Benchmarks
Implicit Reasoning in Deep Time Series Forecasting [NeurIPS Workshop on Time Series in the Age of Large Models 2024] Reasoning-First Benchmarks
Investigating Compositional Reasoning in Time Series Foundation Models [arXiv 2025] Reasoning-First Benchmarks
Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insights [arXiv 2025] Reasoning-First Benchmarks
MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering [arXiv 2025] Reasoning-First Benchmarks
Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement [ACL 2025] Reasoning-First Benchmarks
PUB: Plot Understanding Benchmark and Dataset for Evaluating Large Language Models on Synthetic Visual Data Interpretation [arXiv 2024] Reasoning-First Benchmarks
Context is Key: A Benchmark for Forecasting with Essential Textual Information [ICML 2025] Reasoning-First Benchmarks
TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents [arXiv 2025] Reasoning-First Benchmarks
SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series [ICLR 2024] Reasoning-First Benchmarks
Inferring Events from Time Series using Language Models [arXiv 2025] Reasoning-First Benchmarks
Intervention-Aware Forecasting: Breaking Historical Limits from a System Perspective [arXiv 2024] Reasoning-First Benchmarks
ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset [ICML 2025] Reasoning-First Benchmarks
AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance [arXiv 2025] Reasoning-First Benchmarks
GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images [arXiv 2025] Reasoning-Ready Benchmarks
See it, Think it, Sorted: Large Multimodal Models are Few-shot Time Series Anomaly Analyzers [arXiv 2024] Reasoning-Ready Benchmarks
GPT4MTS: Prompt-Based Large Language Model for Multimodal Time-Series Forecasting [AAAI 2024] Reasoning-Ready Benchmarks
Multi-Modal Forecaster: Jointly Predicting Time Series and Textual Data [arXiv 2024] Reasoning-Ready Benchmarks
Retrieval-augmented Large Language Models for Financial Time Series Forecasting [arXiv 2025] Reasoning-Ready Benchmarks
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting [ICLR 2024] Reasoning-Ready Benchmarks
Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking [arXiv 2025] Reasoning-Ready Benchmarks
Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning [ICML 2024] Reasoning-Ready Benchmarks
MoTime: A Dataset Suite for Multimodal Time Series Forecasting [arXiv 2025] Reasoning-Ready Benchmarks
Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series [NeurIPS 2025] Reasoning-Ready Benchmarks
Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis [NeurIPS 2024] Reasoning-Ready Benchmarks
TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting [KDD 2025] Reasoning-Ready Benchmarks
Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends [Journal of Forecasting 2024] Reasoning-Ready Benchmarks
Time-RA: Towards Time Series Reasoning for Anomaly with LLM Feedback [arXiv 2025] Reasoning-Ready Benchmarks
A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization [NAACL 2025] General-Purpose Time Series Benchmarks
Are Language Models Actually Useful for Time Series Forecasting? [NeurIPS 2024] General-Purpose Time Series Benchmarks
Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series? [arXiv 2025] General-Purpose Time Series Benchmarks
Can LLMs Understand Time Series Anomalies? [ICLR 2025] General-Purpose Time Series Benchmarks
Can Multimodal LLMs Perform Time Series Anomaly Detection? [arXiv 2025] General-Purpose Time Series Benchmarks
TimeSeriesExam: A Time Series Understanding Exam [NeurIPS Workshop on Time Series in the Age of Large Models 2024] General-Purpose Time Series Benchmarks
Can LLMs Serve As Time Series Anomaly Detectors? [arXiv 2024] General-Purpose Time Series Benchmarks
Language Models Still Struggle to Zero-shot Reason about Time Series [EMNLP 2024] General-Purpose Time Series Benchmarks
Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data [arXiv 2025] General-Purpose Time Series Benchmarks
ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning [VLDB 2025] General-Purpose Time Series Benchmarks
Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis [arXiv 2025] General-Purpose Time Series Benchmarks
FinBen: An Holistic Financial Benchmark for Large Language Models [NeurIPS 2024] General-Purpose Time Series Benchmarks
FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting [arXiv 2025] General-Purpose Time Series Benchmarks
Foundation Models for Time Series Analysis: A Tutorial and Survey [KDD 2024] Surveys and Tutorials
Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review [arXiv 2024] Surveys and Tutorials
Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models [arXiv 2025] Surveys and Tutorials
Integrating Artificial Intelligence Agents with the Internet of Things for Enhanced Environmental Monitoring: Applications in Water Quality and Climate Data [Electronics 2025] Surveys and Tutorials
LLMs Meet Cross-Modal Time Series Analytics: Overview and Directions [arXiv 2025] Surveys and Tutorials
Are Language Models Actually Useful for Time Series Forecasting? [NeurIPS 2024] Position and Vision Papers
Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning [arXiv 2025] Position and Vision Papers
Position: Empowering Time Series Reasoning with Multimodal LLMs [arXiv 2025] Position and Vision Papers
Position: What Can Large Language Models Tell Us about Time Series Analysis [ICML 2024] Position and Vision Papers

How to Contribute

We welcome contributions to keep this table updated. Please follow these steps:

  1. Decide Research vs. Non-Research

    • Research = new methods/analyses with experiments (papers with tasks, tags, etc.).
    • Non-Research = datasets/benchmarks, surveys/tutorials, position/vision papers.
  2. If Research:

  3. If Non-Research:

    • Add the paper under Non-Research Papers in the correct subgroup:
      • Reasoning-First Benchmarks
      • Reasoning-Ready Benchmarks
      • General-Purpose Time Series Benchmarks
      • Surveys and Tutorials
      • Position and Vision Papers
    • No attribute tags for non-research entries.
  4. Formatting rules

    • Use the exact row format already in the tables:
      | [Paper Title](link) [Venue/Year] | <Type or columns per table> |
      
    • Keep venue/year brackets (e.g., [NeurIPS 2024], [arXiv 2025]).
    • Place new rows in chronological order (newest first) within each subgroup/table.
  5. Open a PR

    • Title: Add <Paper Short Title> (<Year>)
    • In the PR body, state:
      • Research vs. non-research
      • Chosen reasoning topology (if research)
      • Primary objective, task, and tags you set
      • Any notes (e.g., multimodal inputs, tools used)

Citation

If you find this resource useful, please cite our survey.

@misc{chang2025surveyreasoningagenticsystems,
      title={A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models}, 
      author={Ching Chang and Yidan Shi and Defu Cao and Wei Yang and Jeehyun Hwang and Haixin Wang and Jiacheng Pang and Wei Wang and Yan Liu and Wen-Chih Peng and Tien-Fu Chen},
      year={2025},
      eprint={2509.11575},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2509.11575}, 
}

About

[TMLR 2026] A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models

Topics

Resources

Stars

57 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors