# Time Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMs

arXiv: https://arxiv.org/abs/2506.10630 · HTML: https://mlsanity.com/paper/2506.10630/

## Key facts

- Cited by 34 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 69 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Placed in

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

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

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [A Survey of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2312.14925/) (2023)
- [TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2402.19072/) (2024)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [Large Language Models for Time Series: A Survey](https://mlsanity.com/paper/2402.01801/) (2024)
- [Empowering Time Series Analysis with Large Language Models: A Survey](https://mlsanity.com/paper/2402.03182/) (2024)
- [LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting](https://mlsanity.com/paper/2402.16132/) (2024)
- [Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting](https://mlsanity.com/paper/2405.14252/) (2024)
- [Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insights](https://mlsanity.com/paper/2503.01895/) (2025)

## Built on by (most cited first, 30 of 34)

- [A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models](https://mlsanity.com/paper/2509.11575/) (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)
- [CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities](https://mlsanity.com/paper/2604.18401/) (2026)
- [STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning](https://mlsanity.com/paper/2601.03248/) (2026)
- [PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization](https://mlsanity.com/paper/2601.10029/) (2026)
- [Adaptive Time Series Reasoning via Segment Selection](https://mlsanity.com/paper/2602.18645/) (2026)
- [A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs](https://mlsanity.com/paper/2506.20073/) (2025)
- [STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models](https://mlsanity.com/paper/2511.11233/) (2025)
- [Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning](https://mlsanity.com/paper/2602.07830/) (2026)
- [LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics](https://mlsanity.com/paper/2604.17295/) (2026)
- [TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning](https://mlsanity.com/paper/2605.00015/) (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)
- [CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting](https://mlsanity.com/paper/2604.27840/) (2026)
- [Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting](https://mlsanity.com/paper/2605.29401/) (2026)
- [WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning](https://mlsanity.com/paper/2606.11816/) (2026)
- [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)
- [Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs](https://mlsanity.com/paper/2605.21975/) (2026)
- [CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting](https://mlsanity.com/paper/2608.03031/) (2026)
- [ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution](https://mlsanity.com/paper/2601.13546/) (2026)
- [CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting](https://mlsanity.com/paper/2602.03564/) (2026)
- [AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection](https://mlsanity.com/paper/2602.08868/) (2026)
- [Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases](https://mlsanity.com/paper/2602.17001/) (2026)
- [GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation](https://mlsanity.com/paper/2604.21501/) (2026)
- [GeoDecider: An Evidence-Grounded Agent for Geological Interpretation via Deliberative Reasoning](https://mlsanity.com/paper/2605.03383/) (2026)
- [Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection](https://mlsanity.com/paper/2605.30344/) (2026)

## Abstract (arXiv)

To advance time series forecasting (TSF), various methods have been proposed to improve prediction accuracy, evolving from statistical techniques to data-driven deep learning architectures. Despite their effectiveness, most existing methods still adhere to a fast thinking paradigm-relying on extracting historical patterns and mapping them to future values as their core modeling philosophy, lacking an explicit thinking process that incorporates intermediate time series reasoning. Meanwhile, emerging slow-thinking LLMs (e.g., OpenAI-o1) have shown remarkable multi-step reasoning capabilities, offering an alternative way to overcome these issues. However, prompt engineering alone presents several limitations - including high computational cost, privacy risks, and limited capacity for in-depth domain-specific time series reasoning. To address these limitations, a more promising approach is to train LLMs to develop slow thinking capabilities and acquire strong time series reasoning skills. For this purpose, we propose Time-R1, a two-stage reinforcement fine-tuning framework designed to enhance multi-step reasoning ability of LLMs for time series forecasting. Specifically, the first stage conducts supervised fine-tuning for warmup adaptation, while the second stage employs reinforcement learning to improve the model's generalization ability. Particularly, we design a fine-grained multi-objective reward specifically for time series forecasting, and then introduce GRIP (group-based relative importance for policy optimization), which leverages non-uniform sampling to further encourage and optimize the model's exploration of effective reasoning paths. Experiments demonstrate that Time-R1 significantly improves forecast performance across diverse datasets.