arXiv · cs.AI · Zhishang Xiang, Yunbo Tang, Zhongqiao Liu, Junkai Chen, Zerui Chen, Qingguo Hu, Yuxuan Zhang, William Grant, Qinggang Zhang, Jinsong Su · 4 小时前模型评分43
EvoMemState：为个人智能体演化记忆状态
EvoMemState: Evolving Memory State for Personal Agents
导读
研究者提出以状态为中心的记忆框架 EvoMemState，在持久事实之外增加关系状态与推理状态，让大语言模型（LLM，Large Language Model）智能体判断哪些记忆适用于当前请求。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “In this paper, we introduce EvoMemState, a state-centric framework that augments persistent facts with two complementary states: Relational States that capture how facts remain valid and relate to one another as memory evolves, and a Reasoning State that determines how these facts should be applied to the current request.”
- “Our code and implementation details are available at this https URL .”
来源：arXiv · cs.AI · arxiv.org