_version_ 1866911371156783104
author Hu, Yuyang
Liu, Shichun
Yue, Yanwei
Zhang, Guibin
Liu, Boyang
Zhu, Fangyi
Lin, Jiahang
Guo, Honglin
Dou, Shihan
Xi, Zhiheng
Jin, Senjie
Tan, Jiejun
Yin, Yanbin
Liu, Jiongnan
Zhang, Zeyu
Sun, Zhongxiang
Zhu, Yutao
Sun, Hao
Peng, Boci
Cheng, Zhenrong
Fan, Xuanbo
Guo, Jiaxin
Yu, Xinlei
Zhou, Zhenhong
Hu, Zewen
Huo, Jiahao
Wang, Junhao
Niu, Yuwei
Wang, Yu
Yin, Zhenfei
Hu, Xiaobin
Liao, Yue
Li, Qiankun
Wang, Kun
Zhou, Wangchunshu
Liu, Yixin
Cheng, Dawei
Zhang, Qi
Gui, Tao
Pan, Shirui
Zhang, Yan
Torr, Philip
Dou, Zhicheng
Wen, Ji-Rong
Huang, Xuanjing
Jiang, Yu-Gang
Yan, Shuicheng
author_facet Hu, Yuyang
Liu, Shichun
Yue, Yanwei
Zhang, Guibin
Liu, Boyang
Zhu, Fangyi
Lin, Jiahang
Guo, Honglin
Dou, Shihan
Xi, Zhiheng
Jin, Senjie
Tan, Jiejun
Yin, Yanbin
Liu, Jiongnan
Zhang, Zeyu
Sun, Zhongxiang
Zhu, Yutao
Sun, Hao
Peng, Boci
Cheng, Zhenrong
Fan, Xuanbo
Guo, Jiaxin
Yu, Xinlei
Zhou, Zhenhong
Hu, Zewen
Huo, Jiahao
Wang, Junhao
Niu, Yuwei
Wang, Yu
Yin, Zhenfei
Hu, Xiaobin
Liao, Yue
Li, Qiankun
Wang, Kun
Zhou, Wangchunshu
Liu, Yixin
Cheng, Dawei
Zhang, Qi
Gui, Tao
Pan, Shirui
Zhang, Yan
Torr, Philip
Dou, Zhicheng
Wen, Ji-Rong
Huang, Xuanjing
Jiang, Yu-Gang
Yan, Shuicheng
contents Memory has emerged, and will continue to remain, a core capability of foundation model-based agents. As research on agent memory rapidly expands and attracts unprecedented attention, the field has also become increasingly fragmented. Existing works that fall under the umbrella of agent memory often differ substantially in their motivations, implementations, and evaluation protocols, while the proliferation of loosely defined memory terminologies has further obscured conceptual clarity. Traditional taxonomies such as long/short-term memory have proven insufficient to capture the diversity of contemporary agent memory systems. This work aims to provide an up-to-date landscape of current agent memory research. We begin by clearly delineating the scope of agent memory and distinguishing it from related concepts such as LLM memory, retrieval augmented generation (RAG), and context engineering. We then examine agent memory through the unified lenses of forms, functions, and dynamics. From the perspective of forms, we identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory. From the perspective of functions, we propose a finer-grained taxonomy that distinguishes factual, experiential, and working memory. From the perspective of dynamics, we analyze how memory is formed, evolved, and retrieved over time. To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks. Beyond consolidation, we articulate a forward-looking perspective on emerging research frontiers, including memory automation, reinforcement learning integration, multimodal memory, multi-agent memory, and trustworthiness issues. We hope this survey serves not only as a reference for existing work, but also as a conceptual foundation for rethinking memory as a first-class primitive in the design of future agentic intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13564
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Memory in the Age of AI Agents
Hu, Yuyang
Liu, Shichun
Yue, Yanwei
Zhang, Guibin
Liu, Boyang
Zhu, Fangyi
Lin, Jiahang
Guo, Honglin
Dou, Shihan
Xi, Zhiheng
Jin, Senjie
Tan, Jiejun
Yin, Yanbin
Liu, Jiongnan
Zhang, Zeyu
Sun, Zhongxiang
Zhu, Yutao
Sun, Hao
Peng, Boci
Cheng, Zhenrong
Fan, Xuanbo
Guo, Jiaxin
Yu, Xinlei
Zhou, Zhenhong
Hu, Zewen
Huo, Jiahao
Wang, Junhao
Niu, Yuwei
Wang, Yu
Yin, Zhenfei
Hu, Xiaobin
Liao, Yue
Li, Qiankun
Wang, Kun
Zhou, Wangchunshu
Liu, Yixin
Cheng, Dawei
Zhang, Qi
Gui, Tao
Pan, Shirui
Zhang, Yan
Torr, Philip
Dou, Zhicheng
Wen, Ji-Rong
Huang, Xuanjing
Jiang, Yu-Gang
Yan, Shuicheng
Computation and Language
Artificial Intelligence
Memory has emerged, and will continue to remain, a core capability of foundation model-based agents. As research on agent memory rapidly expands and attracts unprecedented attention, the field has also become increasingly fragmented. Existing works that fall under the umbrella of agent memory often differ substantially in their motivations, implementations, and evaluation protocols, while the proliferation of loosely defined memory terminologies has further obscured conceptual clarity. Traditional taxonomies such as long/short-term memory have proven insufficient to capture the diversity of contemporary agent memory systems. This work aims to provide an up-to-date landscape of current agent memory research. We begin by clearly delineating the scope of agent memory and distinguishing it from related concepts such as LLM memory, retrieval augmented generation (RAG), and context engineering. We then examine agent memory through the unified lenses of forms, functions, and dynamics. From the perspective of forms, we identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory. From the perspective of functions, we propose a finer-grained taxonomy that distinguishes factual, experiential, and working memory. From the perspective of dynamics, we analyze how memory is formed, evolved, and retrieved over time. To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks. Beyond consolidation, we articulate a forward-looking perspective on emerging research frontiers, including memory automation, reinforcement learning integration, multimodal memory, multi-agent memory, and trustworthiness issues. We hope this survey serves not only as a reference for existing work, but also as a conceptual foundation for rethinking memory as a first-class primitive in the design of future agentic intelligence.
title Memory in the Age of AI Agents
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2512.13564