# Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting

arXiv: https://arxiv.org/abs/2505.24511 · HTML: https://mlsanity.com/paper/2505.24511/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Time series reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 82 references that are in the map.
- First posted on arXiv 30 May 2025.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [A Multi-Horizon Quantile Recurrent Forecaster](https://mlsanity.com/paper/1711.11053/) (2017)
- [Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning](https://mlsanity.com/paper/2502.18080/) (2025)
- [Context is Key: A Benchmark for Forecasting with Essential Textual Information](https://mlsanity.com/paper/2410.18959/) (2024)
- [Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals](https://mlsanity.com/paper/2310.00603/) (2023)
- [When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning](https://mlsanity.com/paper/2504.01005/) (2025)
- [Towards Time Series Reasoning with LLMs](https://mlsanity.com/paper/2409.11376/) (2024)
- [Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights](https://mlsanity.com/paper/2502.12521/) (2025)
- [Provable Scaling Laws for the Test-Time Compute of Large Language Models](https://mlsanity.com/paper/2411.19477/) (2024)
- [Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification](https://mlsanity.com/paper/2410.18686/) (2024)
- [How Much Can Time-related Features Enhance Time Series Forecasting?](https://mlsanity.com/paper/2412.01557/) (2024)

## Built on by (most cited first, 20 of 20)

- [TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models](https://mlsanity.com/paper/2509.24803/) (2025)
- [A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models](https://mlsanity.com/paper/2509.11575/) (2025)
- [PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature](https://mlsanity.com/paper/2510.10909/) (2025)
- [TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting](https://mlsanity.com/paper/2510.00461/) (2025)
- [Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting](https://mlsanity.com/paper/2602.01776/) (2026)
- [MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning](https://mlsanity.com/paper/2602.03164/) (2026)
- [STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning](https://mlsanity.com/paper/2601.03248/) (2026)
- [Are LLMs Stable Formal Logic Translators in Logical Reasoning Across Linguistically Diversified Texts?](https://mlsanity.com/paper/2506.04575/) (2025)
- [STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models](https://mlsanity.com/paper/2511.11233/) (2025)
- [From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents](https://mlsanity.com/paper/2604.19775/) (2026)
- [Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision](https://mlsanity.com/paper/2510.16980/) (2025)
- [TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modeling](https://mlsanity.com/paper/2511.07968/) (2025)
- [From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation](https://mlsanity.com/paper/2512.03360/) (2025)
- [Chain-of-thought Reviewing and Correction for Time Series Question Answering](https://mlsanity.com/paper/2512.22627/) (2025)
- [TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning](https://mlsanity.com/paper/2603.07528/) (2026)
- [CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting](https://mlsanity.com/paper/2602.03564/) (2026)
- [Efficient Test-Time Scaling for LLM-based Time Series Forecasting](https://mlsanity.com/paper/2608.08675/) (2026)
- [A Human-in-the-Loop Autonomous Agent for Industry Time Series Forecasting](https://mlsanity.com/paper/2608.30976/) (2026)
- [JudgeCast: Time Series Forecasting with Experience-Informed Covariate Judgements](https://mlsanity.com/paper/2609.36966/) (2026)
- [DualCast: A Dual-Path Language Model for Bimodal Financial Time-Series Forecasting](https://mlsanity.com/paper/2609.38197/) (2026)

## Abstract (arXiv)

Time series forecasting (TSF) is a fundamental and widely studied task, spanning methods from classical statistical approaches to modern deep learning and multimodal language modeling. Despite their effectiveness, these methods often follow a fast thinking paradigm emphasizing pattern extraction and direct value mapping, while overlooking explicit reasoning over temporal dynamics and contextual dependencies. Meanwhile, emerging slow-thinking LLMs (e.g., ChatGPT-o1, DeepSeek-R1) have demonstrated impressive multi-step reasoning capabilities across diverse domains, suggesting a new opportunity for reframing TSF as a structured reasoning task. This motivates a key question: can slow-thinking LLMs effectively reason over temporal patterns to support time series forecasting, even in zero-shot manner? To investigate this, in this paper, we propose TimeReasoner, an extensive empirical study that formulates TSF as a conditional reasoning task. We design a series of prompting strategies to elicit inference-time reasoning from pretrained slow-thinking LLMs and evaluate their performance across diverse TSF benchmarks. Our findings reveal that slow-thinking LLMs exhibit non-trivial zero-shot forecasting capabilities, especially in capturing high-level trends and contextual shifts. While preliminary, our study surfaces important insights into the reasoning behaviors of LLMs in temporal domains highlighting both their potential and limitations. We hope this work catalyzes further research into reasoning-based forecasting paradigms and paves the way toward more interpretable and generalizable TSF frameworks.