AI Memory, specifically how models organizes and retrieves historical messages, becomes increasingly valuable to Large Language Models (LLMs), yet existing methods (RAG and Graph-RAG) primarily retrieve memory through similarity-based mechanisms. While efficient, such System-1-style retrieval struggles with scenarios that require global reasoning or comprehensive coverage of all relevant information. In this work, We propose Mnemis, a novel memory framework that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection. Mnemis organizes memory into a base graph for similarity retrieval and a hierarchical graph that enables top-down, deliberate traversal over semantic hierarchies. By combining the complementary strength from both retrieval routes, Mnemis retrieves memory items that are both semantically and structurally relevant. Mnemis achieves state-of-the-art performance across all compared methods on long-term memory benchmarks, scoring 93.9 on LoCoMo and 91.6 on LongMemEval-S using GPT-4.1-mini.

翻译：人工智能记忆，特别是模型如何组织和检索历史信息，对大型语言模型（LLM）日益重要，然而现有方法（RAG与Graph-RAG）主要依赖基于相似性的检索机制。这类系统1型检索虽效率较高，但在需要全局推理或全面覆盖所有相关信息的情境中表现不足。本研究提出Mnemis——一种新颖的记忆框架，它将系统1相似性搜索与互补的系统2机制（称为全局选择）相结合。Mnemis将记忆组织为基础图（用于相似性检索）和层次图（支持沿语义层次进行自上而下的精细化遍历）。通过融合双路径检索的互补优势，Mnemis能够检索出在语义和结构层面均相关的记忆单元。在长期记忆基准测试中，Mnemis在所有对比方法中均取得最优性能：使用GPT-4.1-mini时，在LoCoMo上获得93.9分，在LongMemEval-S上获得91.6分。