Accès ouvert déclaré
2025
preprint
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Team, Aohan Zeng, Xin Lü, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Dongqin Yin, Hao Zeng, Jiajie Zhang, Kedong Wang, Lucen Zhong, M. Liu, Rui Lü, Shulin Cao, Xiaohan Zhang, Xuancheng Huang, Yean Cheng, Yu An, Yilin Niu, Y. K. Wen, Yushi Bai, Zhengxiao Du, Zihan Wang, Zilin Zhu, Bohan Zhang, Bosi Wen, Bowen Wu, Baolei Xu, Can Huang, Changpeng Cai, Chao Yu, Chen Li, Chunhua Ge, Cheng-Hua Huang, Chenhui Zhang, Chenxi Xu, Chenzheng Zhu, Chuang Li, Dayong Yang, Dazhi Jiang, Ding Ai, Erle Zhu, Fei Wang, Guoqiang Pan, Wang Guo, Hailong Sun, Haitao Li, Haiyang Li, Hongbo Hu, Hanyu Zhang, Hao Peng, Hao Tai, H. Zhang, Haoran Wang, Haoyu Yang, He Liu, He Zhao, Hongwei Liu, H.H. Yan, Huan Liu, Huilong Chen, Li Ji, Jiajing Zhao, Jiamin Ren, Jian Jiao, Jiani Zhao, Jiaqi Wang, Jiayi Gui, Jiayue Zhao, Jie Liu, Jijie Li, Jing Li, Jing Lu, Jingsen Wang, Jingwei Yuan, Jingxuan Li, Jianbing Du, Jinhua Du, Jinxin Liu, Junkai Zhi, Junli Gao, Ke Wang, Likun Yang, Liangfei Xu, Lin Fan, Lindong Wu, Lintao Ding, Lu Wang, Man Zhang, Minghao Li, Minrui Xu, Mingming Zhao, Mingshu Zhai, Pengfan Du, Qian Dong, Shangqing Tu, Shangtong Yang, Shaoyou Lu, Shijie Li, Shuang Li, Shuang-Li, Shuxun Yang, Sibo Yi, Tianshu Yu, Wei Tian, W.L. Wang, Wen‐Tao Yu, Weng Lam Tam, Wenjie Liang, Wentao Liu, Xiao Wang, Xiaohan Jia, Xiaotao Gu, X. Ling, Xin Wang, Fan Xing, Xinyuan Zhang, Xinze Zhang, Xiuqing Fu, Yabo Xu, Yandong Wu, Yong‐Jie Lu, Yidong Wang, Yilin Zhou, Yiming Pan, Ying Zhang, Yingli Wang, Yingru Li, Yinpei Su, Yipeng Geng, Yitong Zhu, Yongkun Yang, Yuhang Li, Yuhao Wu, Yujiang Li, Yunan Liu, Yunqing Wang, Yuntao Li, Yuxuan Zhang, Zezhen Liu, Zhen Yang, Zhengda Zhou, Zhaohui Qiao, Zhuoer Feng, Zhuorui Liu, Zichen Zhang, Zijun Yao, Zikang Wang, Ziqiang Liu, Ziwei Chai, Zixuan Li, Zuodong Zhao, Wenguang Chen, Jidong Zhai, Bin Xu, Minlie Huang, Hongning Wang, Juanzi Li, Yuxiao Dong, Jie Tang
5Citations signalées, ce qui n’est pas une note de qualité
0Institutions déclarées
0Pays d’affiliation déclarés
Le résumé fourni par la source
We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes. Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding (ARC) tasks, scoring 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified. With much fewer parameters than several competitors, GLM-4.5 ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks. We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems. Code, models, and more information are available at https://github.com/zai-org/GLM-4.5.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
La source scientifique ouverte est momentanément indisponible.
Les sujets associés
Distributed and Parallel Computing SystemsRough Sets and Fuzzy LogicCognitive Computing and Networks