论文提出 MemoType 按记忆类型路由检索
一篇论文提出 MemoType 机制，按记忆与查询的类型分类并分别采用对应检索策略，证明单一检索策略在多类型记忆库中存在期望精度上界，并发布带类型标签的 TriMEM 数据集用于训练分类器。实验显示 Recall@1 在三个数据集上最高提升 16.18%。
Nice paper on agent memory.
It explores an effective routing mechanism for memory in agents.
The overall finding is that you want a separate retrieval strategy for each type of memory instead of one embedding search over everything.
The authors prove that any single retrieval strategy has an upper bound on expected precision when the memory store holds several types.
MemoType classifies each memory and each query by type, retrieves memories that match the query type, and applies the strategy for that type. A new dataset, TriMEM, provides the type labels needed to train the classifier.
Recall@1 improves by up to 16.18% across three datasets.
Paper: academy.dair.ai/papers/memor…
来源：dair_ai · x.com