Xu, Ran, Zhuang, Yuchen, Dong, Zihan, Wang, Ruiyu, Yu, Yue, Ho, Joyce C, Zhang, Linjun, Wang, Haoyu, Shi, Wenqi, and Yang, Carl. AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play. Retrieved from https://par.nsf.gov/biblio/10680889.

Xu, Ran, Zhuang, Yuchen, Dong, Zihan, Wang, Ruiyu, Yu, Yue, Ho, Joyce C, Zhang, Linjun, Wang, Haoyu, Shi, Wenqi, & Yang, Carl. AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play. Retrieved from https://par.nsf.gov/biblio/10680889.

Xu, Ran, Zhuang, Yuchen, Dong, Zihan, Wang, Ruiyu, Yu, Yue, Ho, Joyce C, Zhang, Linjun, Wang, Haoyu, Shi, Wenqi, and Yang, Carl. "AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play". Country unknown/Code not available: The Thirty-ninth Annual Conference on Neural Information Processing Systems. https://par.nsf.gov/biblio/10680889.

@article{osti_10680889,
place = {Country unknown/Code not available}, title = {AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play}, url = {https://par.nsf.gov/biblio/10680889}, abstractNote = {}, journal = {}, publisher = {The Thirty-ninth Annual Conference on Neural Information Processing Systems}, author = {Xu, Ran and Zhuang, Yuchen and Dong, Zihan and Wang, Ruiyu and Yu, Yue and Ho, Joyce C and Zhang, Linjun and Wang, Haoyu and Shi, Wenqi and Yang, Carl}, }