# A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization

arXiv: https://arxiv.org/abs/2411.06018 · HTML: https://mlsanity.com/paper/2411.06018/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Placed in Time series reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 56 references that are in the map.
- First posted on arXiv 9 Nov 2024.

## Placed in

- LLM reasoning / [Time series reasoning](https://mlsanity.com/lr/time-series-reasoning/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [TrustLLM: Trustworthiness in Large Language Models](https://mlsanity.com/paper/2401.05561/) (2024)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models](https://mlsanity.com/paper/2410.09671/) (2024)
- [Language Models Still Struggle to Zero-shot Reason about Time Series](https://mlsanity.com/paper/2404.11757/) (2024)
- [Many-Shot In-Context Learning in Multimodal Foundation Models](https://mlsanity.com/paper/2405.09798/) (2024)
- [TimeSeriesExam: A time series understanding exam](https://mlsanity.com/paper/2410.14752/) (2024)
- [Towards Time Series Reasoning with LLMs](https://mlsanity.com/paper/2409.11376/) (2024)
- [TSI-Bench: Benchmarking Time Series Imputation](https://mlsanity.com/paper/2406.12747/) (2024)
- [On the Out-Of-Distribution Generalization of Multimodal Large Language Models](https://mlsanity.com/paper/2402.06599/) (2024)
- [ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding](https://mlsanity.com/paper/2408.11363/) (2024)
- [Can LLMs Serve As Time Series Anomaly Detectors?](https://mlsanity.com/paper/2408.03475/) (2024)
- [MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models](https://mlsanity.com/paper/2409.19492/) (2024)
- [LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain](https://mlsanity.com/paper/2404.02127/) (2024)

## Built on by (most cited first, 30 of 33)

- [Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement](https://mlsanity.com/paper/2503.01875/) (2025)
- [A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models](https://mlsanity.com/paper/2509.11575/) (2025)
- [How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook](https://mlsanity.com/paper/2503.11835/) (2025)
- [TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning](https://mlsanity.com/paper/2506.13705/) (2025)
- [Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insights](https://mlsanity.com/paper/2503.01895/) (2025)
- [ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response](https://mlsanity.com/paper/2604.21199/) (2026)
- [Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learning](https://mlsanity.com/paper/2510.01116/) (2025)
- [TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction](https://mlsanity.com/paper/2510.01111/) (2025)
- [LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models](https://mlsanity.com/paper/2512.23025/) (2025)
- [Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning](https://mlsanity.com/paper/2602.07830/) (2026)
- [MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices](https://mlsanity.com/paper/2505.10607/) (2025)
- [Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision](https://mlsanity.com/paper/2510.16980/) (2025)
- [SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning](https://mlsanity.com/paper/2602.19455/) (2026)
- [Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting](https://mlsanity.com/paper/2605.29401/) (2026)
- [TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning](https://mlsanity.com/paper/2607.08940/) (2026)
- [ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction](https://mlsanity.com/paper/2503.20978/) (2025)
- [ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Cross-Modal Alignment Dataset](https://mlsanity.com/paper/2505.10083/) (2025)
- [TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting](https://mlsanity.com/paper/2507.10349/) (2025)
- [Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift](https://mlsanity.com/paper/2510.14814/) (2025)
- [Prompting Underestimates LLM Capability for Time Series Classification](https://mlsanity.com/paper/2601.03464/) (2026)
- [Multi-Modal Time Series Prediction via Mixture of Modulated Experts](https://mlsanity.com/paper/2601.21547/) (2026)
- [From Time Series Analysis to Question Answering: A Survey in the LLM Era](https://mlsanity.com/paper/2506.11512/) (2025)
- [NeuroCanvas: VLLM-Powered Robust Seizure Detection by Reformulating Multichannel EEG as Image](https://mlsanity.com/paper/2602.04769/) (2026)
- [BiomechAgent: AI-Assisted Biomechanical Analysis Through Code-Generating Agents](https://mlsanity.com/paper/2602.06975/) (2026)
- [AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection](https://mlsanity.com/paper/2602.08868/) (2026)
- [KairosVL: Orchestrating Time Series and Semantics for Unified Reasoning](https://mlsanity.com/paper/2602.20494/) (2026)
- [Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents](https://mlsanity.com/paper/2603.11479/) (2026)
- [TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs](https://mlsanity.com/paper/2606.09030/) (2026)
- [Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models](https://mlsanity.com/paper/2606.13624/) (2026)
- [FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering](https://mlsanity.com/paper/2607.18102/) (2026)

## Abstract (arXiv)

Large language models (LLMs), with demonstrated reasoning abilities across multiple domains, are largely underexplored for time-series reasoning (TsR), which is ubiquitous in the real world. In this work, we propose TimerBed, the first comprehensive testbed for evaluating LLMs' TsR performance. Specifically, TimerBed includes stratified reasoning patterns with real-world tasks, comprehensive combinations of LLMs and reasoning strategies, and various supervised models as comparison anchors. We perform extensive experiments with TimerBed, test multiple current beliefs, and verify the initial failures of LLMs in TsR, evidenced by the ineffectiveness of zero shot (ZST) and performance degradation of few shot in-context learning (ICL). Further, we identify one possible root cause: the numerical modeling of data. To address this, we propose a prompt-based solution VL-Time, using visualization-modeled data and language-guided reasoning. Experimental results demonstrate that Vl-Time enables multimodal LLMs to be non-trivial ZST and powerful ICL reasoners for time series, achieving about 140% average performance improvement and 99% average token costs reduction.