@misc{bai2024multi, title={Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining}, author={Tianyi Bai and Ling Yang and Zhen Hao Wong and Jiahui Peng and Xinlin Zhuang and Chi Zhang and Lijun Wu and Qiu Jiantao and Wentao Zhang and Binhang Yuan and Conghui He}, year={2024}, eprint={2410.08102}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2410.08102} }