About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Preston Rasmussen
- sl:arxiv_num : 2501.13956
- sl:arxiv_published : 2025-01-20T16:52:48Z
- sl:arxiv_summary : 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.@en
- sl:arxiv_title : Zep: A Temporal Knowledge Graph Architecture for Agent Memory@en
- sl:arxiv_updated : 2025-01-20T16:52:48Z
- sl:bookmarkOf : https://arxiv.org/abs/2501.13956
- sl:creationDate : 2025-02-18
- sl:creationTime : 2025-02-18T14:47:20Z
Documents with similar tags (experimental)
Preferences...