作者：Logsdon, Glennis A.; Ebert, Peter; Audano, Peter A.; Loftus, Mark; Porubsky, David; Ebler, Jana; Yilmaz, Feyza; Hallast, Pille; Prodanov, Timofey; Yoo, Dongahn; Paisie, Carolyn A.; Harvey, William T.; Zhao, Xuefang; Martino, Gianni V.; Henglin, Mir; Munson, Katherine M.; Rabbani, Keon; Chin, Chen-Shan; Gu, Bida; Ashraf, Hufsah; Scholz, Stephan; Austine-Orimoloye, Olanrewaju; Balachandran, Parithi; Bonder, Marc Jan; Cheng, Haoyu; Chong, Zechen; Crabtree, Jonathan; Gerstein, Mark; Guethlein, Lisbeth A.; Hasenfeld, Patrick; Hickey, Glenn; Hoekzema, Kendra; Hunt, Sarah E.; Jensen, Matthew; Jiang, Yunzhe; Koren, Sergey; Kwon, Youngjun; Li, Chong; Li, Heng; Li, Jiaqi; Norman, Paul J.; Oshima, Keisuke K.; Paten, Benedict; Phillippy, Adam M.; Pollock, Nicholas R.; Rausch, Tobias; Rautiainen, Mikko; Song, Yuwei; Soylev, Arda; Sulovari, Arvis; Surapaneni, Likhitha; Tsapalou, Vasiliki; Zhou, Weichen; Zhou, Ying; Zhu, Qihui; Zody, Michael C.; Mills, Ryan E.; Devine, Scott E.; Shi, Xinghua; Talkowski, Michael E.; Chaisson, Mark J. P.; Dilthey, Alexander T.; Konkel, Miriam K.; Korbel, Jan O.; Lee, Charles; Beck, Christine R.; Eichler, Evan E.; Marschall, Tobias
作者单位：University of Washington; University of Washington Seattle; University of Pennsylvania; Pennsylvania Medicine; Heinrich Heine University Dusseldorf; Heinrich Heine University Dusseldorf; Heinrich Heine University Dusseldorf Hospital; Heinrich Heine University Dusseldorf; Jackson Laboratory; Clemson University; Clemson University; Heinrich Heine University Dusseldorf; Harvard University; Massachusetts Institute of Technology (MIT); Broad Institute; Harvard University; Massachusetts Institute of Technology (MIT); Broad Institute; Harvard University; Harvard University Medical Affiliates; Massachusetts General Hospital; Harvard University; Harvard University Medical Affiliates; Massachusetts General Hospital; Harvard University; Harvard Medical School; Medical University of South Carolina; University of Southern California; Heinrich Heine University Dusseldorf; European Molecular Biology Laboratory (EMBL); European Bioinformatics Institute; University of Groningen; Helmholtz Association; German Cancer Research Center (DKFZ); Yale University; University of Alabama System; University of Alabama Birmingham; University System of Maryland; University of Maryland Baltimore; Yale University; Yale University; Stanford University; Stanford Medicine; European Molecular Biology Laboratory (EMBL); University of California System; University of California Santa Cruz; National Institutes of Health (NIH) - USA; NIH National Human Genome Research Institute (NHGRI); Pennsylvania Commonwealth System of Higher Education (PCSHE); Temple University; Pennsylvania Commonwealth System of Higher Education (PCSHE); Temple University; Harvard University; Harvard University Medical Affiliates; Dana-Farber Cancer Institute; Harvard University; Harvard Medical School; University of Colorado System; University of Colorado Anschutz; University of Colorado System; University of Colorado Anschutz; University of Helsinki; University of Michigan System; University of Michigan; Stanford University; Stanford Medicine; University of Connecticut; Howard Hughes Medical Institute; University of Washington; University of Washington Seattle
作者：Guo, Daya; Yang, Dejian; Zhang, Haowei; Song, Junxiao; Wang, Peiyi; Zhu, Qihao; Xu, Runxin; Zhang, Ruoyu; Ma, Shirong; Bi, Xiao; Zhang, Xiaokang; Yu, Xingkai; Wu, Yu; Wu, Z. F.; Gou, Zhibin; Shao, Zhihong; Li, Zhuoshu; Gao, Ziyi; Liu, Aixin; Xue, Bing; Wang, Bingxuan; Wu, Bochao; Feng, Bei; Lu, Chengda; Zhao, Chenggang; Deng, Chengqi; Ruan, Chong; Dai, Damai; Chen, Deli; Ji, Dongjie; Li, Erhang; Lin, Fangyun; Dai, Fucong; Luo, Fuli; Hao, Guangbo; Chen, Guanting; Li, Guowei; Zhang, H.; Xu, Hanwei; Ding, Honghui; Gao, Huazuo; Qu, Hui; Li, Hui; Guo, Jianzhong; Li, Jiashi; Chen, Jingchang; Yuan, Jingyang; Tu, Jinhao; Qiu, Junjie; Li, Junlong; Cai, J. L.; Ni, Jiaqi; Liang, Jian; Chen, Jin; Dong, Kai; Hu, Kai; You, Kaichao; Gao, Kaige; Guan, Kang; Huang, Kexin; Yu, Kuai; Wang, Lean; Zhang, Lecong; Zhao, Liang; Wang, Litong; Zhang, Liyue; Xu, Lei; Xia, Leyi; Zhang, Mingchuan; Zhang, Minghua; Tang, Minghui; Zhou, Mingxu; Li, Meng; Wang, Miaojun; Li, Mingming; Tian, Ning; Huang, Panpan; Zhang, Peng; Wang, Qiancheng; Chen, Qinyu; Du, Qiushi; Ge, Ruiqi; Zhang, Ruisong; Pan, Ruizhe; Wang, Runji; Chen, R. J.; Jin, R. L.; Chen, Ruyi; Lu, Shanghao; Zhou, Shangyan; Chen, Shanhuang; Ye, Shengfeng; Wang, Shiyu; Yu, Shuiping; Zhou, Shunfeng; Pan, Shuting; Li, S. S.; Zhou, Shuang; Wu, Shaoqing; Yun, Tao; Pei, Tian; Sun, Tianyu; Wang, T.; Zeng, Wangding; Liu, Wen; Liang, Wenfeng; Gao, Wenjun; Yu, Wenqin; Zhang, Wentao; Xiao, W. L.; An, Wei; Liu, Xiaodong; Wang, Xiaohan; Chen, Xiaokang; Nie, Xiaotao; Cheng, Xin; Liu, Xin; Xie, Xin; Liu, Xingchao; Yang, Xinyu; Li, Xinyuan; Su, Xuecheng; Lin, Xuheng; Li, X. Q.; Jin, Xiangyue; Shen, Xiaojin; Chen, Xiaosha; Sun, Xiaowen; Wang, Xiaoxiang; Song, Xinnan; Zhou, Xinyi; Wang, Xianzu; Shan, Xinxia; Li, Y. K.; Wang, Y. Q.; Wei, Y. X.; Zhang, Yang; Xu, Yanhong; Li, Yao; Zhao, Yao; Sun, Yaofeng; Wang, Yaohui; Yu, Yi; Zhang, Yichao; Shi, Yifan; Xiong, Yiliang; He, Ying; Piao, Yishi; Wang, Yisong; Tan, Yixuan; Ma, Yiyang; Liu, Yiyuan; Guo, Yongqiang; Ou, Yuan; Wang, Yuduan; Gong, Yue; Zou, Yuheng; He, Yujia; Xiong, Yunfan; Luo, Yuxiang; You, Yuxiang; Liu, Yuxuan; Zhou, Yuyang; Zhu, Y. X.; Huang, Yanping; Li, Yaohui; Zheng, Yi; Zhu, Yuchen; Ma, Yunxian; Tang, Ying; Zha, Yukun; Yan, Yuting; Ren, Z. Z.; Ren, Zehui; Sha, Zhangli; Fu, Zhe; Xu, Zhean; Xie, Zhenda; Zhang, Zhengyan; Hao, Zhewen; Ma, Zhicheng; Yan, Zhigang; Wu, Zhiyu; Gu, Zihui; Zhu, Zijia; Liu, Zijun; Li, Zilin; Xie, Ziwei; Song, Ziyang; Pan, Zizheng; Huang, Zhen; Xu, Zhipeng; Zhang, Zhongyu; Zhang, Zhen
作者单位：Chinese Academy of Sciences; University of Science & Technology of China, CAS; Peking University; Tsinghua University
摘要：General reasoning represents a long-standing and formidable challenge in artificial intelligence (AI). Recent breakthroughs, exemplified by large language models (LLMs)1,2 and chain-of-thought (CoT) prompting3, have achieved considerable success on foundational reasoning tasks. However, this success is heavily contingent on extensive human-annotated demonstrations and the capabilities of models are still insufficient for more complex problems. Here we show that the reasoning abilities of LLMs ...
