Memora通过结构化设计平衡记忆的抽象与细节，提升智能体推理能力。
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
- 用主抽象索引具体记忆，合并相关更新形成统一条目。
- 在LoCoMo和LongMemEval上达到新最好性能，记忆越长效果越优。
- 适合需要长期记忆与精准推理的复杂智能体系统使用。
智能体记忆系统需持续积累信息，同时支持高效、上下文感知的检索以完成下游任务。抽象对扩展记忆至关重要，但常牺牲细节，影响推理效果。我们提出Memora，一种在结构上平衡抽象与特异性的记忆表示。它通过主抽象索引具体记忆值，并将相关更新合并为统一记忆条目；同时，提示锚点扩展跨多维度的检索路径，连接相关记忆。在此结构基础上，采用主动利用记忆关联的检索策略，实现超越直接语义相似性的信息召回。理论上，标准RAG与基于知识图谱的内存系统均为本框架的特例。实验表明，Memora在LoCoMo与LongMemEval基准上取得新最优结果，证明其在记忆规模增长时仍具更高检索相关性与推理有效性。
原文摘要 · Abstract (English)
Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks. Abstraction is essential for scaling agent memory, yet it often comes at the cost of specificity, obscuring the fine-grained details required for effective reasoning. We introduce Memora, a harmonic memory representation that structurally balances abstraction and specificity. Memora organizes information via its primary abstractions that index concrete memory values and consolidate related updates into unified memory entries, while cue anchors expand retrieval access across diverse aspects of the memory and connect related memories. Building on this structure, we employ a retrieval policy that actively exploits these memory connections to retrieve relevant information beyond direct semantic similarity. Theoretically, we show that standard Retrieval-Augmented Generation (RAG) and Knowledge Graph (KG)-based memory systems emerge as special cases of our framework. Empirically, Memora establishes a new state-of-the-art on the LoCoMo and LongMemEval benchmarks, demonstrating better retrieval relevance and reasoning effectiveness as memory scales.
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。