🐏 TimeOmni-1-7B: 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

Note: All metrics below are computed only on valid responses. “–” indicates a success rate (SR) below 10%; in such cases, results are omitted due to insufficient statistical significance, and we therefore do not report them.

	Task1 ID (ACC↑/SR)	Task1 OOD (ACC↑/SR)	Task2 ID (ACC↑/SR)	Task2 OOD (ACC↑/SR)	Task3 ID (MAE↓/SR)	Task3 OOD (MAE↓/SR)	Task4 ID (ACC↑/SR)	Task4 OOD (ACC↑/SR)
Time Series Language Model
Time-MQA Llama3-8B	32.2/-	29.5/1.4	25.1/-	32.6/0.4	30.1/12.0	44.3/13.3	31.2/11.6	37.2/15.8
Time-MQA Mistral-7B-v0.3	15.1/-	21.5/0.2	27.8/-	22.1/0.0	8.4/5.4	50.2/36.1	4.0/10.0	52.2/47.3
Time-MQA Qwen2.5-7B	25.0/19.76	14.0/12.2	37.5/-	22.7/6.5	29.5/23.8	33.0/58.0	30.5/26.4	32.0/44.3
ChatTS	-/-	6.0/0.0	-/-	6.9/0.0	18.2/5.8	30.1/27.1	18.6/11.1	26.7/27.1
ChatTime-7B-Chat	18.2/11.0	29.8/12.7	-/-	-/-	14.47/100.0	154.55/100.0	-/0.0	-/0.0
ITFormer-7B	43.8/100.0	47.5/100.0	15.0/47.0	14.6/42.0	29.55/96.0	230.04/100.0	25.0/100.0	41.7/100.0
OpenTSLM-llama-3.2-3b-ecg-flamingo	-/5.0	-/3.2	1.6/23.0	3.3/26.5	-/0.2	-/0.0	17.8/98.4	16.2/98.9
Time Series Reasoning Model
Time-R1	30.9/94.0	34.0/92.5	30.2/53.8	31.4/48.9	17.61/38.7	-/6.3	27.8/95.7	32.2/93.1
Ours
TimeOmni-1	90.7/97.5	87.7/98.3	69.3/99.8	64.0/99.8	14.30/93.8	145.53/82.3	47.9/100.0	58.9/100.0

🚀 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. It is finetuned from Qwen2.5-7B-Instruct under Apache 2.0.

✍️ Citation

@article{guan2025timeomni,
  title={Timeomni-1: Incentivizing complex reasoning with time series in large language models},
  author={Guan, Tong and Meng, Zijie and Li, Dianqi and Wang, Shiyu and Yang, Chao-Han Huck and Wen, Qingsong and Liu, Zuozhu and Siniscalchi, Sabato Marco and Jin, Ming and Pan, Shirui},
  journal={arXiv preprint arXiv:2509.24803},
  year={2025}
}