DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments

本研究提出了DeepResearcher，这是一个创新的系统，通过强化学习来辅助深度研究。项目代码已开源：https://github.com/GAIR-NLP/DeepResearcher

Recommended citation: Zheng, Y.*, Fu, D.*, Hu, X.*, Cai, X., Ye, L., Lu, P., & Liu, P. (2024). DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments. arXiv preprint arXiv:2504.03160.
Download Paper