arXiv / Experiential Memory / Token-level

MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

作者：Shengtao Zhang, Jiaqian Wang, Ruiwen Zhou, Junwei Liao, Yuchen Feng, Zhuo Li, Yujie Zheng, Weinan Zhang, Ying Wen, Zhiyu Li, Feiyu Xiong, Yutao Qi, Bo Tang, Muning Wen · 来源：arXiv · 发布日期：2026/01

经验记忆词元级记忆
新标签打开 AlphaXiv
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory figure
AlphaXiv 中文概览（可滚动查看）