arXiv · cs.CL 计算与语言· Peiwen Li (Yale University), Harshit Verma (Yale University), Sophia Zhou (Yale University), Haiwen Wang (Yale University), Ngoc Bui (Yale University), Heng Chang (Tsinghua University), Fei Fei (Goodvision AI), David van Dijk (Yale University), Rex Ying (Yale University)·· 4 小时前AI 评分55
CoReMem：为连续编码任务内化成本的记忆框架
CoReMem: Cost-Internalizing Memory for Successive Coding Tasks with Prospective Valuation
AI 导读
Yale 等机构的研究者提出 CoReMem，一个把记忆写入与读取成本纳入考量的框架，用于指导编码智能体在连续任务中设计记忆并适配行为。
来源：arXiv · cs.CL 计算与语言 · arxiv.org