🐏 TimeOmni-1-4B: Generalized Time Series Reasoning Model

We present TimeOmni-1, the first generalized, unified model for time series reasoning. It first injects temporal priors through supervised fine-tuning. Then, reinforcement learning with task-grounded rewards guides the model beyond mimicking priors toward robust reasoning. Experiments show that TimeOmni-1 achieves top-tier performance while preserving the general reasoning ability of the base model. Finally, we demonstrate that joint training across diverse reasoning tasks yields mutual gains, supporting a “train-once, use-across-tasks” paradigm for future time series reasoning models.

🎨 Task Illustration

🧠 Method

TimeOmni-1 is a generalized reasoning model for time series. Pretrained LLMs often lack temporal priors because they are rarely exposed to time series during pretraining. To address this, we use a two-stage training pipeline: (1) supervised fine-tuning (SFT) to inject temporal priors and anchor the model in a temporal knowledge space, and (2) reinforcement learning (RL) with task-grounded rewards (see Reward Evaluation in the figure above) to improve robustness and reasoning quality.

📊 Benchmarks

Table 1. Overall Benchmark Comparison

Table 2. Model Size Scaling Comparison

🚀 Usage

This repository hosts the model weights for TimeOmni-1. For installation, usage instructions, and further documentation, please visit our GitHub repository.

License

TimeOmni-1 is licensed under the Apache 2.0 license.

✍️ Citation

@inproceedings{
guan2026timeomni,
title={TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models},
author={Tong Guan and Zijie Meng and Dianqi Li and Shiyu Wang and Chao-Han Huck Yang and Qingsong Wen and Zuozhu Liu and Sabato Marco Siniscalchi and Ming Jin and Shirui Pan},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=kOIclg7muL}
}