arXiv Robotics· Minghao Guo, Qingyue Jiao, Xiujin Liu, Jianhong Pang, Ruimeng Yang, Naihao Xu, Liwei Che, Haochen Xue, Ziqi Wang, Xinying Cai, Jiaxuan Luo, Jiaxin Deng, Xuesong Ye, Jintao Qu, Wenyao Gao, Jingwen Gu, Chenyang Zhao, Shichun Liu, Guibin Zhang, Zefang Liu, Siyin Wang, Wujiang Xu, Danrui Li, Zeru Shi, Woongyeong Yeo, Shuang Liu, Wei-Chieh Huang, Weizhi Zhang, Tianyu Yang, Kangsan Kim, Yebowen Hu, Bowen Wen, Bowen Jiang, Haohao Su, Ming Yin, Sheldon Yu, Mian Zhang, Yuyan Chen, Hanrong Zhang, Kai Mei, Zihao Zhang, Mingyu Jin, Xi Zhu, Hengyi Wang, Tianxin Wei, Linyong Nan, Zhenwen Liang, Zhendong Chu, Ziqi Huang, Yongye Su, Sixun Dong, Shujian Liu, Kaiqu Liang, Jiaojiao Han, Zhaoye Fei, Kun Wang, Shihan Dou, Zhichun Guo, Xingjian Diao, Zeqi Gu, Heng Wang, Tao Feng, Cheng Qian, Hamid Palangi, Silei Xu, Xi Yun, Yi Zhu, Shilong Liu, Qingsong Wen, Sung Ju Hwang, Zuxuan Wu, Yu-Gang Jiang, Yiyu Shi, Dimitris N. Metaxas, Jiaxuan You, Julian McAuley, Mengdi Wang, Jiawei Han, Philip S. Yu, Ziyi Ye·· 4 小时前AI 评分24
多模态智能体记忆的演进：从感知、维护到学习
Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory
AI 导读
一篇 arXiv 综述提出多模态智能体记忆的双轴分析框架：轴一关注多模态信息如何形成与表示（如模态专属嵌入向量、文本与结构化记录、潜在与参数化表示），轴二将记忆管理分为 T1 静态记忆、T2 动态记忆和 T3 自演化记忆三个层级。基于该框架，作者归纳了重复出现的设计模式，并提出在来源保真与抽象之间平衡、维护时间有效性与溯源、将记忆使用锚定于可恢复证据、随时间演化记忆策略等原则。
来源：arXiv Robotics · arxiv.org