Zep：用于智能体记忆的时间知识图谱架构
Zep: A Temporal Knowledge Graph Architecture for Agent Memory
AI总结：
Zep 提出时间感知知识图谱架构，通过动态整合对话与业务数据，在记忆检索基准上超越 MemGPT，准确率提升达18.5%，延迟降低90%。
摘要：
我们介绍了 Zep，一种面向 AI 智能体的新型记忆层服务，在深度记忆检索（DMR）基准测试中，其性能优于当前最先进的系统 MemGPT。此外，Zep 在比 DMR 更全面、更具挑战性的评估中表现出色，这些评估更能反映真实世界的企业用例。虽然现有的基于大语言模型（LLM）的智能体的检索增强生成（RAG）框架仅限于静态文档检索，但企业应用需要从包括持续对话和业务数据在内的多种来源进行动态知识整合。Zep 通过其核心组件 Graphiti 解决了这一根本性限制——Graphiti 是一个时间感知的知识图谱引擎，能够动态综合非结构化的对话数据和结构化的业务数据，同时维护历史关系。在 MemGPT 团队将其作为主要评估指标的 DMR 基准测试中，Zep 展现了优越的性能（94.8% 对比 93.4%）。除了 DMR，Zep 的能力还通过更具挑战性的 LongMemEval 基准测试得到进一步验证，该基准通过复杂的时序推理任务更好地反映了企业用例。在此评估中，Zep 取得了显著成果，与基线实现相比，准确率提升最高达 18.5%，同时响应延迟降低了 90%。这些结果在跨会话信息综合和长期上下文维护等企业关键任务中尤为突出，证明了 Zep 在实际应用部署中的有效性。
英文摘要：
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark. Additionally, Zep excels in more comprehensive and challenging evaluations than DMR that better reflect real-world enterprise use cases. While existing retrieval-augmented generation (RAG) frameworks for large language model (LLM)-based agents are limited to static document retrieval, enterprise applications demand dynamic knowledge integration from diverse sources including ongoing conversations and business data. Zep addresses this fundamental limitation through its core component Graphiti -- a temporally-aware knowledge graph engine that dynamically synthesizes both unstructured conversational data and structured business data while maintaining historical relationships. In the DMR benchmark, which the MemGPT team established as their primary evaluation metric, Zep demonstrates superior performance (94.8% vs 93.4%). Beyond DMR, Zep's capabilities are further validated through the more challenging LongMemEval benchmark, which better reflects enterprise use cases through complex temporal reasoning tasks. In this evaluation, Zep achieves substantial results with accuracy improvements of up to 18.5% while simultaneously reducing response latency by 90% compared to baseline implementations. These results are particularly pronounced in enterprise-critical tasks such as cross-session information synthesis and long-term context maintenance, demonstrating Zep's effectiveness for deployment in real-world applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
