mlsanityData to 14 Oct 2026

TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents

arXiv 2502.11418 ↗First posted 17 Feb 2025cs.AI cs.LGcited by 37

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

Abstract (arXiv)

Time series data is essential in various applications, including climate modeling, healthcare monitoring, and financial analytics. Understanding the contextual information associated with real-world time series data is often essential for accurate and reliable event predictions. In this paper, we introduce TimeCAP, a time-series processing framework that creatively employs Large Language Models (LLMs) as contextualizers of time series data, extending their typical usage as predictors. TimeCAP incorporates two independent LLM agents: one generates a textual summary capturing the context of the time series, while the other uses this enriched summary to make more informed predictions. In addition, TimeCAP employs a multi-modal encoder that synergizes with the LLM agents, enhancing predictive performance through mutual augmentation of inputs with in-context examples. Experimental results on real-world datasets demonstrate that TimeCAP outperforms state-of-the-art methods for time series event prediction, including those utilizing LLMs as predictors, achieving an average improvement of 28.75% in F1 score.

Key facts. Cited by 37 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 30 of its 47 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

30 of 47 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  6. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  8. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  9. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  10. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  11. 2024Chronos: Learning the Language of Time Seriescited by 759
  12. 2021Multimodal Few-Shot Learning with Frozen Language Modelscited by 661
18 more
  1. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  2. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 500
  3. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 488
  4. 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 461
  5. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 411
  6. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 256
  7. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 250
  8. 2023Large Language Models as General Pattern Machinescited by 197
  9. 2022Can large language models reason about medical questions?cited by 194
  10. 2022Can Foundation Models Wrangle Your Data?cited by 175
  11. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 169
  12. 2023Prompting Large Language Models with Speech Recognition Abilitiescited by 140
  13. 2023Large Language Models are Few-Shot Health Learnerscited by 118
  14. 2024Large Language Models for Time Series: A Surveycited by 114
  15. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 110
  16. 2024Empowering Time Series Analysis with Large Language Models: A Surveycited by 60
  17. 2023Leveraging Large Language Models for Pre-trained Recommender Systemscited by 42
  18. 2023SaDI: A Self-adaptive Decomposed Interpretable Framework for Electric Load Forecasting under Extreme Eventscited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 21; 2026: 16.

37 papers.

Sort:

By area:

  1. 2025MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answeringcited by 55
  2. 2025TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loopcited by 39
  3. 2025Foundation Models for Spatio-Temporal Data Science: A Tutorial and Surveycited by 24
  4. 2025Multi-modal Time Series Analysis: A Tutorial and Surveycited by 24
  5. 2025A Survey of Reasoning and Agentic Systems in Time Series with Large Language Modelscited by 21
  6. 2025TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learningcited by 18
  7. 2026TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Taskscited by 17
  8. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 16
  9. 2025SciTS: Scientific Time Series Understanding and Generation with LLMscited by 15
  10. 2025Low-bit Model Quantization for Deep Neural Networks: A Surveycited by 11
  11. 2025Diffusion Models for Time Series Forecasting: A Surveycited by 11
  12. 2025TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrievalcited by 7
25 more
  1. 2025Text Reinforcement for Multimodal Time Series Forecastingcited by 7
  2. 2025LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessmentcited by 6
  3. 2025Context-Aware Probabilistic Modeling with LLM for Multimodal Time Series Forecastingcited by 4
  4. 2025TsLLM: Augmenting LLMs for General Time Series Understanding and Predictioncited by 4
  5. 2026Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoningcited by 3
  6. 2026Harnessing Generalist Agents for Contextualized Time Seriescited by 3
  7. 2025EventTSF: Event-Aware Non-Stationary Time Series Forecastingcited by 2
  8. 2025DS-Diffusion: Data Style-Guided Diffusion Model for Time-Series Generationcited by 2
  9. 2025Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Visioncited by 2
  10. 2026GlyRAG: Context-Aware Retrieval-Augmented Framework for Blood Glucose Forecastingcited by 2
  11. 2026TimeClaw: A Time-Series AI Agent with Exploratory Execution Learningcited by 2
  12. 2026MILM: Large Language Models for Multimodal Irregular Time Series with Informative Samplingcited by 2
  13. 2026Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understandingcited by 1
  14. 2026LLM Agents for Time-Series: A Surveycited by 1
  15. 2025Fewer yet critical: Reducing Redundant Token Dependencies for Transformer-based Time Series Forecastingcited by 0
  16. 2025Generalised Label-free Artefact Cleaning for Real-time Medical Pulsatile Time Seriescited by 0
  17. 2025Auditable Context-Aware HFMD Forecasting with Structured LLM Agentscited by 0
  18. 2026COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completioncited by 0
  19. 2026Learning to Select Source-Traceable Evidence for Language-Model Prediction from Irregular Clinical Time Seriescited by 0
  20. 2026TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMscited by 0
  21. 2026SCENARIODIFF: A Scenario-level Guidance Framework for Multimodal Time Series Forecasting--Extended Versioncited by 0
  22. 2026Can Large Language Models Explain Flight Safety Events? A Prior-Guided Semantic LLM-based Approachcited by 0
  23. 2026SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecastingcited by 0
  24. 2026FreSia: Frequency-Semantic Instantiation and Alignment for Multivariate Time Series Analysiscited by 0
  25. 2026MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Visioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale
  2. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
  3. 2025Large Language models for Time Series Analysis: Techniques, Applications, and Challenges
  4. 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
  5. 2024Understanding Why Large Language Models Can Be Ineffective in Time Series Analysis: The Impact of Modality Alignment
  6. 2025Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting
  7. 2025When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
  8. 2025Semantic-Enhanced Time-Series Forecasting via Large Language Models