提出双路径记忆检索框架，提升大模型长期记忆的全面性与准确性。
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory
- 构建基础图与分层图双通道，融合快速相似搜索与深度结构遍历。
- 在LoCoMo和LongMemEval-S上分别达到93.9和91.6得分，超越现有方法。
- 适合需要全局推理与完整信息覆盖的长期记忆应用场景。
人工智能记忆对大语言模型日益重要，但现有方法（如RAG和Graph-RAG）主要依赖基于相似性的检索，虽高效却难以处理需全局推理或全面覆盖信息的场景。本文提出Mnemis，一种新型记忆框架，将系统1的相似性检索与系统2的全局选择机制结合。该框架在基础图中实现语义相似性检索，在分层图中支持自顶向下的语义层次遍历。通过双路径互补，Mnemis能同时捕捉语义与结构相关的信息。在长期记忆基准测试中，使用GPT-4.1-mini，Mnemis在LoCoMo上取得93.9分，在LongMemEval-S上取得91.6分，性能达当前最优。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。