Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, S. H. Cai, Yuan Cao, Ziwei Chai, Y. Charles, Cheng Chen, Guanduo Chen, Huarong Chen, Jia Chen, Jiahao Chen, Jianlong Chen, Jun Chen, Kefan Chen, Liang Chen, Ruijue Chen, Xinhao Chen, Yanru Chen, Yanxu Chen, Yicun Chen, Yimin Chen, Yingjiang Chen, Yuankun Chen, Yujie Chen, Yutian Chen, Zhirong Chen, Ziwei Chen, Dazhi Cheng, Yean Cheng, Minghan Chu, Jialei Cui, Jiaqi Deng, Muxi Diao, Mengfan Dong, Mengnan Dong, Yuxin Dong, Yuhao Dong, Yuhao Dong, Chenzhuang Du, Dikang Du, Lingxiao Du, Yulun Du, Yulun Du, Shengjun Fang, Qiulin Feng, Yichen Feng, Yichen Feng, Kelin Fu, Kelin Fu, Tong Gao, Tong Gao, Shangyi Geng, Chengyang Gong, Xiaochen Gong, Zhuoma Gongque, Zhuoma Gongque, Xinran Gu, Yicheng Gu, Longyu Guan, Longyu Guan, Shuhao Guan, Yuanying Guo, Xiaoru Hao, Yi He, Tianhong He, Hao Hu, Jiaxi Hu, Yangyang Hu, Zhenxing Hu, Chao Hong, Ruiyuan Huang, Weixiao Huang, Zhiqi Huang, Zhenxing Hu, Ke Huang, Ruiyuan Huang, Weixiao Huang, Zhiqi Huang, Chaobo Jia, Tao Jiang, Zhejun Jiang, Xinyi Jin, Yu Jing, Guanyu Li, Haitao Li, Haoyang Li, Jia Li, Jingwei Li, Junxiong Li, Lincan Li, Mo Li, Weihong Li, Wentao Li, Xinhang Li, Xinhao Li, Yang Li, Yanhao Li, Yiwei Li
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of techniques such as joint text-vision pre-training, zero-vision SFT, and joint text-vision reinforcement learning. Building on this multimodal foundation, K2.5 introduces Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently. Extensive evaluations show that Kimi K2.5 achieves state-of-the-art results across various domains including coding, vision, reasoning, and agentic tasks. Agent Swarm also reduces latency by up to $4.5\times$ over single-agent baselines. We release the post-trained Kimi K2.5 model checkpoint to facilitate future research and real-world applications of agentic intelligence.