GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Agentic AI
Published: arXiv: 2508.06471v1
Authors

GLM-4. 5 Team : Aohan Zeng Xin Lv Qinkai Zheng Zhenyu Hou Bin Chen Chengxing Xie Cunxiang Wang Da Yin Hao Zeng Jiajie Zhang Kedong Wang Lucen Zhong Mingdao Liu Rui Lu Shulin Cao Xiaohan Zhang Xuancheng Huang Yao Wei Yean Cheng Yifan An Yilin Niu Yuanhao Wen Yushi Bai Zhengxiao Du Zihan Wang Zilin Zhu Bohan Zhang Bosi Wen Bowen Wu Bowen Xu Can Huang Casey Zhao Changpeng Cai Chao Yu Chen Li Chendi Ge Chenghua Huang Chenhui Zhang Chenxi Xu Chenzheng Zhu Chuang Li Congfeng Yin Daoyan Lin Dayong Yang Dazhi Jiang Ding Ai Erle Zhu Fei Wang Gengzheng Pan Guo Wang Hailong Sun Haitao Li Haiyang Li Haiyi Hu Hanyu Zhang Hao Peng Hao Tai Haoke Zhang Haoran Wang Haoyu Yang He Liu He Zhao Hongwei Liu Hongxi Yan Huan Liu Huilong Chen Ji Li Jiajing Zhao Jiamin Ren Jian Jiao Jiani Zhao Jianyang Yan Jiaqi Wang Jiayi Gui Jiayue Zhao Jie Liu Jijie Li Jing Li Jing Lu Jingsen Wang Jingwei Yuan Jingxuan Li Jingzhao Du Jinhua Du Jinxin Liu Junkai Zhi Junli Gao Ke Wang Lekang Yang Liang Xu Lin Fan Lindong Wu Lintao Ding Lu Wang Man Zhang Minghao Li Minghuan Xu Mingming Zhao Mingshu Zhai Pengfan Du Qian Dong Shangde Lei Shangqing Tu Shangtong Yang Shaoyou Lu Shijie Li Shuang Li Shuang-Li Shuxun Yang Sibo Yi Tianshu Yu Wei Tian Weihan Wang Wenbo Yu Weng Lam Tam Wenjie Liang Wentao Liu Xiao Wang Xiaohan Jia Xiaotao Gu Xiaoying Ling Xin Wang Xing Fan Xingru Pan Xinyuan Zhang Xinze Zhang Xiuqing Fu Xunkai Zhang Yabo Xu Yandong Wu Yida 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 Zhongpei Qiao Zhuoer Feng Zhuorui Liu Zichen Zhang Zihan Wang 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

View on arXiv Download PDF View Graph

Abstract

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.

Paper Summary

Key Innovation
The key innovation is the development of two new models, GLM-4.5 and GLM-4.5-Air, which are open-source Mixture-of-Experts (MoE) large language models that feature hybrid reasoning modes: thinking mode for complex reasoning and agentic tasks, and non-thinking mode for instant responses. These models demonstrate strong performance on a range of benchmarks in agentic, reasoning, and coding tasks.
Practical Impact
This research has practical impact because it provides a unified foundation model for various applications, such as web search, code generation, and scientific problem-solving. The GLM-4.5 and GLM-4.5-Air models can be used to advance research in reasoning and agentic AI systems, and their open-source nature makes them accessible to the broader research community.
Analogy / Intuitive Explanation
Think of a large language model like a super-smart personal assistant that can understand and respond to various types of requests. Just as you would train your personal assistant to perform different tasks, such as making reservations or sending emails, these GLM models are trained to excel in agentic, reasoning, and coding tasks. The hybrid reasoning modes allow them to adapt to different situations, just like a human would adjust their approach depending on the task at hand. In summary, this research paper introduces two new open-source large language models that demonstrate strong performance across various benchmarks in agentic, reasoning, and coding tasks. These models have practical impact by providing a unified foundation for advancing research in AI systems.
Paper Information
Categories:
cs.CL
Published Date:

arXiv ID:

2508.06471v1

Quick Actions
Back to Home