@misc{zhou2025sweet, title={SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks}, author={Yifei Zhou and Song Jiang and Yuandong Tian and Jason Weston and Sergey Levine and Sainbayar Sukhbaatar and Xian Li}, year={2025}, eprint={2503.15478}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2503.15478} }