| title | Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale |
|---|---|
| authors | Ang Li, Ben Liu, Bin Han, Bin Hu, Bin Jing, Binbin Hu, Bing Li, Cai Chen, Caizhi Tang, Changxin Tian, Chao Huang, Chao Zhang, Chen Liang, Chen Qian, Chengfu Tang, Chengyao Wen, Chilin Fu, Chunwei Wu, Cong Zhang, Cunyin Peng, Daixin Wang, Dalong Zhang, Deng Zhao, Dingnan Jin, Dingyuan Zhu, Donghao Zhang, Fan Yuan, Fangzheng Zhao, Fanzhuang Meng, Feifan Wu, Feng Xu, Fengbin Fang, Gangshan Wang, Guodong Yang, Hailin Zhao, Haitao Wang, Haitao Zhang, Hanxiao Zhang, Hanzi Wang, Hao Dai, Hao Liu, Hao Qian, Hao Wu, Haoxiong Liu, Haoyu Xu, Heng Zhang, Hong Liu, Hongliang Zhang, Hongrui Liu, Hongxun Li, Hongzhi Ruan, Huaidong Xiong, Huihuang Zheng, Huikang Tang, Jia Guo, Jia Li, Jia Liu, Jiameng Wang, Jiaming Liu, Jiannan Shi, Jianping Wei, Jiaolong Yang, Jiapeng Wang, Jie Gao, Jie Wang, Jiewei Wu, Jin Yang, Jinjin Li, Jinjing Huang, Jinquan Sun, Jinyao Chen, Juanhui Tu, Jun Liu, Jun Mei, Jun Xu, Jun Zhou, Junjie Ou, Junnan Sipan, Junpeng Fang, Kaihong Zhang, Kaiqin Hu, Ke Shi, Kuan Xu, Kun Tang, Kunlong Chen, Lanyin Mei, Lei Chen, Lei Liang, Lei Xu, Li Tang, Liang Jiang, Liangcheng Fu, Lihui Zhang, Linfeng Shi, Lintao Ma, Liyuan Liu, Longfei Li, Longfei Zheng, Lu Liu, Lu Yu, Man Li, Meiqi Zhu, Meng Li, Mengjie Gao, Mengshu Sun, Mingming Yin, Mingyang Zhang, Mingyuan Fan, Nuo Xu, Pan Tang, Peijie Jiang, Peilong Zhao, Peng Lin, Pingping Liu, Qi Zuo, Qian Zhao, Qiang Cheng, Qianggang Cao, Qiaoben Bao, Qing Cui, Qingyuan Yang, Qitao Shi, Qiyin Huang, Qizheng Zhou, Quan Wan, Runyuan Zhao, Shaomian Zheng, Shaowei Wei, Shengnan Zhang, Shuaicheng Li, Shujie Li, Shuo Zhang, Sikang Bian, Tianchu Yao, Tiange Xu, Tianshu Wang, Ting Guo, Tinghao Wang, Tingwei Huang, Tong Zhao, Tongkai Yang, Wang Hong, Wanli Gu, Wei Lu, Weichang Wu, Weiguang Han, Weiquan Li, Wenbo Shen, Wenjing Fang, Wenzhi Tang, Xiang Shu, Xiao Shi, Xiaodong Yan, Xiaolu Zhang, Xiaopei Wan, Xiaqing Sun, Xin Zhao, Xingyu Lu, Xinxing Yang, Xinyao Tang, Xinyu Kong, Xinyu Liu, Xiong Xu, Xuan Sun, Xudong Han, Xudong Wang, Xujie Shen, Yalin Zhang, Yangyang Hou, Yankun Ren, Yao Zhao, Ye Chen, Yeyang Chen, Yibo Cao, Yifan Zuo, Yijie Chen, Ying Li, Yingjie Song, Yingxue Li, Yiqi Wang, Yixuan Sun, Yizhu Xiao, Yongfei Xu, Yu Liu, Yuchen Fang, Yue Gao, Yue Yu, Yue Zhang, Yuqi Zhang, Yuxiao He, Yuxiao Lu, Yuxin Tian, Yuxuan Li, Yuzhuo Fu, Zhankai Xu, Zhaoxin Huan, Zhenduo Zhang, Zhengke Gui, Zhengyu Huang, Zhenjun Ma, Zhenxuan Pan, Zheping Qu, Zhibo Zhu, Zhidong Fan, Zhigang Huangfu, Zhihao Wang, Zhiqiang Zhang, Zhizhen Liu, Zhuyan Zhou, Zibin Lin, Zihang Zeng, Zihao Wang, Zilong Wang, Ziqi Liu, Zitao Xuan, Zixuan Cheng, Zujie Wen, Zuoli Tang |
| date | 2026-06-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.15079 |
| affiliation | inclusionAI |
| upvotes | 81 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence. |
cite
@misc{li2026ling,
title={Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale},
author={Ang Li and Ben Liu and Bin Han and Bin Hu and Bin Jing and Binbin Hu and Bing Li and Cai Chen and Caizhi Tang and Changxin Tian and Chao Huang and Chao Zhang and Chen Liang and Chen Qian and Chengfu Tang and Chengyao Wen and Chilin Fu and Chunwei Wu and Cong Zhang and Cunyin Peng and Daixin Wang and Dalong Zhang and Deng Zhao and Dingnan Jin and Dingyuan Zhu and Donghao Zhang and Fan Yuan and Fangzheng Zhao and Fanzhuang Meng and Feifan Wu and Feng Xu and Fengbin Fang and Gangshan Wang and Guodong Yang and Hailin Zhao and Haitao Wang and Haitao Zhang and Hanxiao Zhang and Hanzi Wang and Hao Dai and Hao Liu and Hao Qian and Hao Wu and Haoxiong Liu and Haoyu Xu and Heng Zhang and Hong Liu and Hongliang Zhang and Hongrui Liu and Hongxun Li and Hongzhi Ruan and Huaidong Xiong and Huihuang Zheng and Huikang Tang and Jia Guo and Jia Li and Jia Liu and Jiameng Wang and Jiaming Liu and Jiannan Shi and Jianping Wei and Jiaolong Yang and Jiapeng Wang and Jie Gao and Jie Wang and Jiewei Wu and Jin Yang and Jinjin Li and Jinjing Huang and Jinquan Sun and Jinyao Chen and Juanhui Tu and Jun Liu and Jun Mei and Jun Xu and Jun Zhou and Junjie Ou and Junnan Sipan and Junpeng Fang and Kaihong Zhang and Kaiqin Hu and Ke Shi and Kuan Xu and Kun Tang and Kunlong Chen and Lanyin Mei and Lei Chen and Lei Liang and Lei Xu and Li Tang and Liang Jiang and Liangcheng Fu and Lihui Zhang and Linfeng Shi and Lintao Ma and Liyuan Liu and Longfei Li and Longfei Zheng and Lu Liu and Lu Yu and Man Li and Meiqi Zhu and Meng Li and Mengjie Gao and Mengshu Sun and Mingming Yin and Mingyang Zhang and Mingyuan Fan and Nuo Xu and Pan Tang and Peijie Jiang and Peilong Zhao and Peng Lin and Pingping Liu and Qi Zuo and Qian Zhao and Qiang Cheng and Qianggang Cao and Qiaoben Bao and Qing Cui and Qingyuan Yang and Qitao Shi and Qiyin Huang and Qizheng Zhou and Quan Wan and Runyuan Zhao and Shaomian Zheng and Shaowei Wei and Shengnan Zhang and Shuaicheng Li and Shujie Li and Shuo Zhang and Sikang Bian and Tianchu Yao and Tiange Xu and Tianshu Wang and Ting Guo and Tinghao Wang and Tingwei Huang and Tong Zhao and Tongkai Yang and Wang Hong and Wanli Gu and Wei Lu and Weichang Wu and Weiguang Han and Weiquan Li and Wenbo Shen and Wenjing Fang and Wenzhi Tang and Xiang Shu and Xiao Shi and Xiaodong Yan and Xiaolu Zhang and Xiaopei Wan and Xiaqing Sun and Xin Zhao and Xingyu Lu and Xinxing Yang and Xinyao Tang and Xinyu Kong and Xinyu Liu and Xiong Xu and Xuan Sun and Xudong Han and Xudong Wang and Xujie Shen and Yalin Zhang and Yangyang Hou and Yankun Ren and Yao Zhao and Ye Chen and Yeyang Chen and Yibo Cao and Yifan Zuo and Yijie Chen and Ying Li and Yingjie Song and Yingxue Li and Yiqi Wang and Yixuan Sun and Yizhu Xiao and Yongfei Xu and Yu Liu and Yuchen Fang and Yue Gao and Yue Yu and Yue Zhang and Yuqi Zhang and Yuxiao He and Yuxiao Lu and Yuxin Tian and Yuxuan Li and Yuzhuo Fu and Zhankai Xu and Zhaoxin Huan and Zhenduo Zhang and Zhengke Gui and Zhengyu Huang and Zhenjun Ma and Zhenxuan Pan and Zheping Qu and Zhibo Zhu and Zhidong Fan and Zhigang Huangfu and Zhihao Wang and Zhiqiang Zhang and Zhizhen Liu and Zhuyan Zhou and Zibin Lin and Zihang Zeng and Zihao Wang and Zilong Wang and Ziqi Liu and Zitao Xuan and Zixuan Cheng and Zujie Wen and Zuoli Tang},
year={2026},
eprint={2606.15079},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.15079}
}