[📜 Paper] • [🐱 GitHub]

Repo for "MUR: Momentum Uncertainty Guided Reasoning For Large Language Models"

• [2025/07/22] 🔥🔥🔥 Our paper is released !!!
• [2025/07/19] 🔥🔥🔥 Our github repo is released!!!

MUR reduces computation by over 50% on average across three backbone models, while improving accuracy by 0.62–3.37%.

To use MUR, we can try with the following command.

Firstly, create the environment and install the requirements. This implementation is accelerated and supported by vllm.

# env
conda create -n mur python==3.11.9
conda activate mur
pip install -r requirements.txt

Next, simply run different python files:

python [TTS setting]-[per_step_scale|mur].py

Finally, run eval files. To be specific, please eval gpqa_diamond dataset using eval/eval_gpqa_cot.py. Adiitionaly, use eval/math_verifier.py to verify math datasets.

Feel free to contact with me if you have any questions ~~~

If you find it helpful, please kindly cite our paper.

@article{yan2025mur,
  title={MUR: Momentum Uncertainty guided Reasoning for Large Language Models},
  author={Hang Yan, Fangzhi Xu, Rongman Xu, Yifei Li, Jian Zhang, Haoran Luo, Xiaobao Wu, Luu Anh Tuan, Haiteng Zhao, Qika Lin, Jun Liu},
  journal={arXiv preprint arXiv:2507.14958},
  year={2025}
}