@article{scalingdomaindatarepetitioninllmpretrain, title = {Scaling Domain Data Repetition in LLM Pretraining}, author = {Jingwei Li and Xinran Gu and Rui Dai and Xintong Hao and Chengyin Xu and Yan Wu and Shuran Zheng and Jingzhao Zhang}, year = {2026}, eprint = {2608.14071}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.14071}, }