Sign up to save your podcasts
Or
Share 【第203期】Zep：用临时知识图谱作Agent记忆
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
【第203期】Zep：用临时知识图谱作Agent记忆
Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。
进群添加小助手微信：seventy3_podcast
备注：小宇宙
今天的主题是：Zep: A Temporal Knowledge Graph Architecture for Agent MemorySummary
This paper introduces Zep, a novel memory layer service for AI agents powered by Graphiti, a temporally-aware knowledge graph engine. Zep aims to overcome limitations of current retrieval-augmented generation (RAG) frameworks by dynamically integrating unstructured conversation data and structured business data while preserving historical relationships. Evaluations demonstrate Zep's superior performance over the state-of-the-art MemGPT in the Deep Memory Retrieval benchmark and significant improvements in accuracy and latency in the more challenging LongMemEval benchmark, which better reflects real-world enterprise use cases. The authors also discuss limitations of existing memory benchmarks and suggest future research directions, including integrating other GraphRAG approaches, exploring domain-specific ontologies, and developing more robust evaluation metrics focused on real-world applications and system scalability.
这篇论文介绍了Zep，一种为AI代理提供的全新记忆层服务，其由Graphiti（一个具备时间感知的知识图引擎）驱动。Zep旨在克服当前检索增强生成（RAG）框架的局限，通过动态整合非结构化对话数据和结构化业务数据，同时保持历史关系的连贯性。
评估结果表明，Zep在深度记忆检索基准（Deep Memory Retrieval）测试中优于最先进的MemGPT，并在更具挑战性的LongMemEval基准中显著提高了准确性和延迟，这一基准更好地反映了现实世界中的企业应用场景。
作者还讨论了现有记忆基准的局限性，并提出了未来的研究方向，包括整合其他GraphRAG方法、探索领域特定本体论、以及开发更强大的评估指标，重点关注现实世界应用和系统可扩展性。
原文链接：https://arxiv.org/abs/2501.13956
View all episodes
By 任雨山Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。
进群添加小助手微信：seventy3_podcast
备注：小宇宙
今天的主题是：Zep: A Temporal Knowledge Graph Architecture for Agent MemorySummary
This paper introduces Zep, a novel memory layer service for AI agents powered by Graphiti, a temporally-aware knowledge graph engine. Zep aims to overcome limitations of current retrieval-augmented generation (RAG) frameworks by dynamically integrating unstructured conversation data and structured business data while preserving historical relationships. Evaluations demonstrate Zep's superior performance over the state-of-the-art MemGPT in the Deep Memory Retrieval benchmark and significant improvements in accuracy and latency in the more challenging LongMemEval benchmark, which better reflects real-world enterprise use cases. The authors also discuss limitations of existing memory benchmarks and suggest future research directions, including integrating other GraphRAG approaches, exploring domain-specific ontologies, and developing more robust evaluation metrics focused on real-world applications and system scalability.
这篇论文介绍了Zep，一种为AI代理提供的全新记忆层服务，其由Graphiti（一个具备时间感知的知识图引擎）驱动。Zep旨在克服当前检索增强生成（RAG）框架的局限，通过动态整合非结构化对话数据和结构化业务数据，同时保持历史关系的连贯性。
评估结果表明，Zep在深度记忆检索基准（Deep Memory Retrieval）测试中优于最先进的MemGPT，并在更具挑战性的LongMemEval基准中显著提高了准确性和延迟，这一基准更好地反映了现实世界中的企业应用场景。
作者还讨论了现有记忆基准的局限性，并提出了未来的研究方向，包括整合其他GraphRAG方法、探索领域特定本体论、以及开发更强大的评估指标，重点关注现实世界应用和系统可扩展性。
原文链接：https://arxiv.org/abs/2501.13956