mlsanityData to 14 Oct 2026

Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning

arXiv 2605.09395 ↗First posted 10 May 2026cs.AI cs.LG cs.MAcited by 0

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

Abstract (arXiv)

In this paper, we propose the first VLunderlineM underlineagentic underlinereasoning framework for few-underlineshot multimodal underlineTime underlineSeries underlineClassification (textscMarsTSC), which introduces a self-evolving knowledge bank as a dynamic context iteratively refined via reflective agentic reasoning. The framework comprises three collaborative roles: i) Generator conducts reliable classification via reasoning; ii) Reflector diagnoses the root causes of reasoning errors to yield discriminative insights targeting the temporal features overlooked by Generator; iii) Modifier applies verified updates to the knowledge bank to prevent context collapse. We further introduce a test-time update strategy to enable cautious, continuous knowledge bank refinement to mitigate few-shot bias and distribution shift. Extensive experiments across 12 mainstream time series benchmark datasets demonstrate that method delivers substantial and consistent performance gains across 5 VLM backbones, outperforming both classical and foundation model-based time series baselines under few-shot conditions, while producing interpretable rationales that ground each classification decision in human-readable feature evidence. Code is available at https://github.com/HuangJW0821/MarsTSC.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 41 of its 82 references that are in the map. First posted on arXiv 10 May 2026.

Builds on

41 of 82 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation20 Jan
  2. 2025Structured Agentic Workflows for Financial Time-Series Modeling with LLMs and Reflective Feedback19 Aug

Other references · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  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. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  9. 2024Chronos: Learning the Language of Time Seriescited by 759
  10. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  11. 2018The UEA multivariate time series classification archive, 2018cited by 338
  12. 2014Recurrent Neural Network Regularizationcited by 189
27 more
  1. 2023LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasterscited by 129
  2. 2021HIVE-COTE 2.0: a new meta ensemble for time series classificationcited by 118
  3. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 110
  4. 2024Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Expertscited by 95
  5. 2023Language Model Self-improvement by Reinforcement Learning Contemplationcited by 75
  6. 2021Time Series Prediction using Deep Learning Methods in Healthcarecited by 74
  7. 2023Deep Learning for Time Series Classification and Extrinsic Regression: A Current Surveycited by 68
  8. 2025Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecastingcited by 63
  9. 2024aeon: a Python toolkit for learning from time seriescited by 47
  10. 2025TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loopcited by 39
  11. 2018Deep Air Quality Forecasting Using Hybrid Deep Learning Frameworkcited by 33
  12. 2025Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learningcited by 33
  13. 2025Harnessing Vision Models for Time Series Analysis: A Surveycited by 26
  14. 2025Multi-modal Time Series Analysis: A Tutorial and Surveycited by 24
  15. 2024Plots Unlock Time-Series Understanding in Multimodal Modelscited by 9
  16. 2025Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecastingcited by 9
  17. 2024TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Modelscited by 8
  18. 2025Enhancing LLM Reasoning for Time Series Classification by Tailored Thinking and Fused Decisioncited by 8
  19. 2025From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?cited by 7
  20. 2026Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interactioncited by 3
  21. 2023A Closer Look at Bearing Fault Classification Approachescited by 2
  22. 2024Exploring Explainable AI Techniques for Improved Interpretability in Lung and Colon Cancer Classificationcited by 2
  23. 2025Can Time-Series Foundation Models Perform Building Energy Management Tasks?cited by 2
  24. 2025Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Visioncited by 2
  25. 2024Enhanced Fault Detection and Cause Identification Using Integrated Attention Mechanismcited by 1
  26. 2025Explainable-AI powered stock price prediction using time series transformers: A Case Study on BIST100cited by 1
  27. 2026MM-ISTS: Cooperating Irregularly Sampled Time Series Forecasting with Multimodal Vision-Text LLMscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Training-Free Time Series Classification via In-Context Reasoning with LLM Agents
  2. 2024Towards Time Series Reasoning with LLMs
  3. 2024Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification
  4. 2025Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework
  5. 2026Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning
  6. 2025TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering
  7. 2025TempoGPT: Enhancing Time Series Reasoning via Quantizing Embedding
  8. 2026InstructTime++: Time Series Classification with Multimodal Language Modeling via Implicit Feature Enhancement