让大模型长期记忆像文档一样可维护，支持持续更新与检索。
Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory
- 将记忆组织成主题文档，按语义聚合证据并保留元信息。
- 在MemoryAgentBench上取得64.7%的综合得分，优于传统记忆方式。
- 适合需要长期记忆、频繁更新和多轮推理的智能体应用。
长期运行的大语言模型智能体需要能追踪变化事实并跨会话提供相关证据的持久化记忆系统。现有记忆系统常将观察结果存储为孤立记录、摘要或索引片段，导致证据聚合、事实修订和记忆维护困难。我们提出Infini Memory，一种基于文本的可维护持久化记忆架构，将智能体记忆视为结构化的主题文档。每个主题文档作为语义单元，用于收集相关证据、保留元数据，并随时间修订事实。新观察首先暂存于缓冲区，定期整合为连贯的文本上下文。推理时，通过迭代工具调用的代理式检索机制，让大模型逐步读取记忆，而非一次检索完成。在MemoryAgentBench测试中，Infini Memory取得64.7%的综合得分。消融实验表明，主题结构化维护与迭代证据检查分别提升了长时记忆使用的不同方面。
原文摘要 · Abstract (English)
Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions. Existing memory systems often store observations as isolated records, summaries, or indexed fragments, which makes evidence aggregation, fact revision, and memory maintenance difficult. We propose Infini Memory, a maintainable text-based persistent memory architecture that treats agent memory as topic-structured documents. Each topic document serves as a semantic unit for collecting related evidence, preserving metadata, and revising facts over time. New observations are first staged in a buffer and periodically consolidated into coherent textual contexts. At inference time, an agentic retrieval procedure lets the LLM read memory through iterative tool calls rather than a single retrieval step. On MemoryAgentBench, Infini Memory achieves 64.7% overall score. Ablations show that topic-structured maintenance and iterative evidence inspection improve complementary aspects of long-term memory use.
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。