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

arXiv: https://arxiv.org/abs/2605.09395 · HTML: https://mlsanity.com/paper/2605.09395/

## 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.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [The UEA multivariate time series classification archive, 2018](https://mlsanity.com/paper/1811.00075/) (2018)
- [Recurrent Neural Network Regularization](https://mlsanity.com/paper/1409.2329/) (2014)
- [LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters](https://mlsanity.com/paper/2308.08469/) (2023)
- [HIVE-COTE 2.0: a new meta ensemble for time series classification](https://mlsanity.com/paper/2104.07551/) (2021)
- [Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook](https://mlsanity.com/paper/2310.10196/) (2023)
- [Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts](https://mlsanity.com/paper/2410.10469/) (2024)
- [Language Model Self-improvement by Reinforcement Learning Contemplation](https://mlsanity.com/paper/2305.14483/) (2023)
- [Time Series Prediction using Deep Learning Methods in Healthcare](https://mlsanity.com/paper/2108.13461/) (2021)
- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting](https://mlsanity.com/paper/2502.04395/) (2025)
- [aeon: a Python toolkit for learning from time series](https://mlsanity.com/paper/2406.14231/) (2024)
- [TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop](https://mlsanity.com/paper/2503.01013/) (2025)
- [Deep Air Quality Forecasting Using Hybrid Deep Learning Framework](https://mlsanity.com/paper/1812.04783/) (2018)
- [Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.24726/) (2025)
- [Harnessing Vision Models for Time Series Analysis: A Survey](https://mlsanity.com/paper/2502.08869/) (2025)
- [TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation](https://mlsanity.com/paper/2601.13653/) (2026)
- [Multi-modal Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2503.13709/) (2025)
- [Plots Unlock Time-Series Understanding in Multimodal Models](https://mlsanity.com/paper/2410.02637/) (2024)
- [Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting](https://mlsanity.com/paper/2505.24003/) (2025)
- [Structured Agentic Workflows for Financial Time-Series Modeling with LLMs and Reflective Feedback](https://mlsanity.com/paper/2508.13915/) (2025)

## 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.