AtomMem: Learnable Dynamic Agentic Memory with Atomic Memory Operation
Aug 15, 2026·,,
·
0 min read
Yupeng Huo
Yaxi Lu
Zhong Zhang
Haotian Chen
Supervisor
,Yankai Lin
Abstract
We propose AtomMem, a learnable dynamic agentic memory built from atomic memory operations, so that an agent learns when and how to write, update, and retrieve memory instead of relying on hand-crafted memory pipelines.
Type
Publication
In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)
Authors
Haotian Chen
(he/him)
Research Assistant Professor · LLM Post-Training / AI4AI
I am a Research Assistant Professor at the School of Artificial Intelligence, Shanghai Jiao Tong University, where I work with Prof. Junchi Yan at RethinkLab. I study how to build AI systems that can automate long-horizon, effort-intensive, and creativity-demanding tasks such as research, engineering, and development. My current work focuses on LLM post-training for autonomous agents, agent memory and continual learning, and AI4Research / AI4AI. Before joining SJTU, I received my PhD in Data Science from Fudan University, advised by Prof. Xiangdong Zhou, and completed postdoctoral research at Tsinghua University (THUNLP), working with Prof. Zhiyuan Liu and Prof. Maosong Sun. I was also a research intern at the Machine Learning Research Group of Microsoft Research Asia, mentored by Xiao Yang, and at the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, working with Prof. Yang Yu.