MemT 1.0开源记忆原生基础模型
MemTensor发布并开源MemT 1.0，包含MemT-1.0-Nano和MemT-1.0-Flash两款记忆原生基础模型。该架构采用Gated DeltaNet-2与Mixture-of-Storage，以可持续更新的内部记忆状态参与生成；作者自报其在长历史推理效率、存储占用和智能体任务成功率方面取得提升。报道同时指出，在长历史细节的精确召回上，外部文本记忆系统仍具优势。
MemT 1.0把持续更新的记忆直接集成进模型计算，而非仅依赖外部检索，为降低长历史KV cache成本并在智能体任务中复用程序性经验提供了一条开源路径。
Computer Science > Computation and Language
arXiv:2610.26825 (cs)
[Submitted on 19 Oct 2026]
Title:MemT-1.0: Towards Memory-Native Evolution
Authors:Zhiyu Li, Zeyu Zhang, Linyun Liu, Yiwei Bu, Chenyang Xi, Xichong Zhang, Yi Yu, Yu Yu, Zhichen Liu, Yuxiao Yi, Chunyu Li, Haoran Liu, Zhenkai Ding, Le Zhou, Juncheng Zhang, Boyu Chen, Zehao Lin, Guorui Li, Renyu Fu, Ji Li, Youyang Xia, Jiajun Shen, Harvey Li, Jingsong Zhou, Helan Hu, Tong Shen, Tianxiao Xu, Chenye Han, Weijie Li, Zhongquan Zhou, Hongming Xu, Yuekeng Li, Erenkai Zhu, Peng Yu, Wenhao Li, Jingyi Kang, Xixuan Hao, Xuzhou Zhu, Can Chen, Jiawei Liu, Chen Jiang, Tao Jiang, Fangwei Xiang, Zepeng Yao, Kai Chen, Guang Yang, Mingfei Lu, Chunhui Li, Zhengxuan Jiang, Bo Tang, Shiyu Zhan, Yihang Sun, Jie Chu, Wenjun Xiong, Zhenxiang Hua, Chen Lin, Detong Su, Dongyu Deng, Qiuping Ding, Guofeng Ding, Si Chen, Guohua Wen, Xu Chen, Zhi-Qin John Xu
View a PDF of the paper titled MemT-1.0: Towards Memory-Native Evolution, by Zhiyu Li and 73 other authors
部分来源内容未展示，可前往原文继续阅读。
#MemTensor#MemT-1.0-Nano#MemT-1.0-Flash#Gated DeltaNet-2#Mixture-of-Storage#Qwen3.6-35B-A3B#DeepSeek-V4-Flash#MemOS