# TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models

arXiv: https://arxiv.org/abs/2509.24803 · HTML: https://mlsanity.com/paper/2509.24803/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 76 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 30 of 53)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning](https://mlsanity.com/paper/2002.04326/) (2020)
- [Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization](https://mlsanity.com/paper/2504.05812/) (2025)
- [FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective](https://mlsanity.com/paper/2311.06190/) (2023)
- [TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis](https://mlsanity.com/paper/2410.16032/) (2024)
- [ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data](https://mlsanity.com/paper/2412.11376/) (2024)
- [UniTS: A Unified Multi-Task Time Series Model](https://mlsanity.com/paper/2403.00131/) (2024)
- [Language Models Still Struggle to Zero-shot Reason about Time Series](https://mlsanity.com/paper/2404.11757/) (2024)
- [Context is Key: A Benchmark for Forecasting with Essential Textual Information](https://mlsanity.com/paper/2410.18959/) (2024)
- [Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement](https://mlsanity.com/paper/2503.01875/) (2025)
- [Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning](https://mlsanity.com/paper/2503.18013/) (2025)
- [SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM](https://mlsanity.com/paper/2504.14286/) (2025)

## Built on by (most cited first, 27 of 27)

- [TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models](https://mlsanity.com/paper/2601.18744/) (2026)
- [HEARTS: Benchmarking LLM Reasoning on Health Time Series](https://mlsanity.com/paper/2603.06638/) (2026)
- [Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting](https://mlsanity.com/paper/2602.01776/) (2026)
- [STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning](https://mlsanity.com/paper/2601.03248/) (2026)
- [TimeOmni-VL: Unified Models for Time Series Understanding and Generation](https://mlsanity.com/paper/2602.17149/) (2026)
- [ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response](https://mlsanity.com/paper/2604.21199/) (2026)
- [KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning](https://mlsanity.com/paper/2605.30002/) (2026)
- [PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering](https://mlsanity.com/paper/2602.23161/) (2026)
- [Thoth: Mid-Training Bridges LLMs to Time Series Understanding](https://mlsanity.com/paper/2603.01042/) (2026)
- [CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series](https://mlsanity.com/paper/2607.09880/) (2026)
- [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)
- [AION: Next-Generation Tasks and Practical Harness for Time Series](https://mlsanity.com/paper/2605.25045/) (2026)
- [Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting](https://mlsanity.com/paper/2605.29401/) (2026)
- [Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs](https://mlsanity.com/paper/2605.21975/) (2026)
- [LVCG: Learning ECG Representations in the Latent Vectorcardiogram Space](https://mlsanity.com/paper/2605.31249/) (2026)
- [TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning](https://mlsanity.com/paper/2606.03629/) (2026)
- [A Cost-Effective Multimodal LLM Reasoning Framework for Question Answering over Irregular Clinical Time Series](https://mlsanity.com/paper/2607.25947/) (2026)
- [From Recognition to Understanding: Unlocking Cognitive Time Series Reasoning with LLMs](https://mlsanity.com/paper/2606.22126/) (2026)
- [CodeTS: Verifiable Text-to-Time Series Generation via Executable Code](https://mlsanity.com/paper/2609.15393/) (2026)
- [When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting](https://mlsanity.com/paper/2609.24862/) (2026)
- [TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series](https://mlsanity.com/paper/2609.26389/) (2026)
- [OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning](https://mlsanity.com/paper/2609.40265/) (2026)
- [Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning](https://mlsanity.com/paper/2610.04942/) (2026)
- [Do Time-Series QA Systems Read the Time Series? Evidence Use and Reasoning Reliability](https://mlsanity.com/paper/2610.05686/) (2026)
- [Lapras: Latent Reasoning for Time Series Language Models](https://mlsanity.com/paper/2610.11111/) (2026)
- [GIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation](https://mlsanity.com/paper/2610.17794/) (2026)

## Abstract (arXiv)

Recent advances in multimodal time series learning underscore a paradigm shift from analytics centered on basic patterns toward advanced time series understanding and reasoning. However, existing multimodal time series datasets mostly remain at the level of surface alignment and question answering, without reaching the depth of genuine reasoning. The absence of well-defined tasks that genuinely require time series reasoning, along with the scarcity of high-quality data, has limited progress in building practical time series reasoning models (TSRMs). To this end, we introduce Time Series Reasoning Suite (TSR-Suite), which formalizes four atomic tasks that span three fundamental capabilities for reasoning with time series: (1) perception, acquired through scenario understanding and causality discovery; (2) extrapolation, realized via event-aware forecasting; and (3) decision-making, developed through deliberation over perception and extrapolation. TSR-Suite is the first comprehensive time series reasoning suite that supports not only thorough evaluation but also the data pipeline and training of TSRMs. It contains more than 23K samples, of which 2.3K are carefully curated through a human-guided hierarchical annotation process. Building on this foundation, we introduce TimeOmni-1, the first unified reasoning model designed to address diverse real-world problems demanding time series reasoning. The model is trained in multiple stages, integrating a mixture of task scenarios, novel reward functions, and tailored optimizations. Experiments show that TimeOmni-1 delivers strong out-of-distribution generalization across all tasks and achieves a high rate of valid responses. It significantly improves causality discovery accuracy (64.0% vs. 35.9% with GPT-4.1) and raises the valid response rate by over 6% compared to GPT-4.1 on the event-aware forecasting task.