Zep: A Temporal Knowledge Graph Architecture for Agent Memory

• URL: http://arxiv.org/abs/2501.13956v1
• Date: Mon, 20 Jan 2025 16:52:48 GMT
• Title: Zep: A Temporal Knowledge Graph Architecture for Agent Memory
• Abstract summary: Zep is a novel memory layer service for AI agents.<n>It outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval benchmark.
• Score: 0.11224172067715701
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models [54.53236295237077]
  We introduce RepoReasoner, a benchmark for evaluating repository-level code reasoning.<n> Output Prediction measures fine-grained, stateful execution reasoning across files.<n>Call Chain Prediction evaluates high-level architectural dependency understanding under noisy context.
  arXiv  Detail & Related papers  (2026-07-28T17:12:41Z)
• SE-GA: Memory-Augmented Self-Evolution for GUI Agents [17.051355070847166]
  Self-Evolving GUI Agent (SE-GA) is a novel framework that integrates hierarchical memory structures with an iterative self-improvement mechanism.<n>To ensure continuous learning, we introduce Memory-Augmented Self-Evolution (MASE)
  arXiv  Detail & Related papers  (2026-05-16T08:51:57Z)
• Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage [89.58253972744531]
  Retrieval-augmented generation (RAG) systems combine document retrieval with a generative model to address complex information seeking tasks like report generation.<n>We investigate whether upstream retrieval metrics can serve as reliable early indicators of the final generated response's information coverage.<n>Our findings demonstrate strong correlations between coverage-based retrieval metrics and nugget coverage in generated responses at both topic and system levels.
  arXiv  Detail & Related papers  (2026-03-09T18:20:20Z)
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents [80.33280979339123]
  We introduce Memory-T1, a framework that learns a time-aware memory selection policy using reinforcement learning (RL)<n>On the Time-Dialog benchmark, Memory-T1 boosts a 7B model to an overall score of 67.0%, establishing a new state-of-the-art performance for open-source models.
  arXiv  Detail & Related papers  (2025-12-23T06:37:29Z)
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory [89.65731902036669]
  Evo-Memory is a streaming benchmark and framework for evaluating self-evolving memory in large language model (LLM) agents.<n>We evaluate over ten representative memory modules and evaluate them across 10 diverse multi-turn goal-oriented and single-turn reasoning and QA datasets.
  arXiv  Detail & Related papers  (2025-11-25T21:08:07Z)
• Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs [54.502280390499756]
  We propose TimeWarp to create a targeted synthetic temporal dataset to fine-tune the model's responses to encourage it to focus on the given input video.<n>We demonstrate that when our method is applied to existing models, it significantly improves performance on temporal understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-04T21:48:40Z)
• MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments [6.12783571098263]
  MEMTRACK is a benchmark designed to evaluate long-term memory and state tracking in multi-platform agent environments.<n>Each benchmark instance provides a chronologically platform-interleaved timeline, with noisy, conflicting, cross-referring information.<n>Our benchmark tests memory capabilities such as acquistion, selection and conflict resolution.
  arXiv  Detail & Related papers  (2025-10-01T18:34:03Z)
• KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues [58.305425399644086]
  Multi-Turn Long-Form Question Answering (MT-LFQA) is a key application paradigm of Large Language Models (LLMs) in knowledge-intensive domains.<n>We introduce textbfKnowMT-Bench, the textitfirst-ever benchmark designed to systematically evaluate MT-LFQA for LLMs across knowledge-intensive fields.
  arXiv  Detail & Related papers  (2025-09-26T04:32:29Z)
• Fun-ASR Technical Report [89.84148151617022]
  We present Fun-ASR, a large-scale, LLM-based ASR system that combines massive data, large model capacity, LLM integration, and reinforcement learning.<n>Fun-ASR is specifically optimized for practical deployment, with enhancements in streaming capability, noise robustness, code-switching, hotword customization, and satisfying other real-world application requirements.<n>Thanks to production-oriented optimizations, Fun-ASR achieves state-of-the-art performance on real application datasets, demonstrating its effectiveness and robustness in practical settings.
  arXiv  Detail & Related papers  (2025-09-15T23:19:36Z)
• Towards Reliable Multi-Agent Systems for Marketing Applications via Reflection, Memory, and Planning [0.5828668695854936]
  We introduce a framework called RAMP that iteratively plans, calls tools, verifies the output, and generates suggestions to improve the quality of the audience generated.<n>We equip the model with a long-term memory store, which is a knowledge base of client-specific facts and past queries.<n>Overall, we demonstrate the use of LLM planning and memory, which increases accuracy by 28 percentage points on a set of 88 evaluation queries.
  arXiv  Detail & Related papers  (2025-08-14T23:52:39Z)
• Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
  We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
  arXiv  Detail & Related papers  (2025-06-29T08:34:59Z)
• FindingDory: A Benchmark to Evaluate Memory in Embodied Agents [49.89792845476579]
  We introduce a new benchmark for long-range embodied tasks in the Habitat simulator.<n>This benchmark evaluates memory-based capabilities across 60 tasks requiring sustained engagement and contextual awareness.
  arXiv  Detail & Related papers  (2025-06-18T17:06:28Z)
• StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns [7.60350050736492]
  Long-term memory is essential for large language models to achieve autonomous intelligence.<n>Existing benchmarks face challenges in evaluating knowledge retention and dynamic sequential reasoning.<n>We propose a novel benchmark framework based on interactive fiction games.
  arXiv  Detail & Related papers  (2025-06-16T10:54:31Z)
• ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search [53.40810298627443]
  ReGUIDE is a framework for web grounding that enables MLLMs to learn data efficiently through self-generated reasoning and spatial-aware criticism.<n>Our experiments demonstrate that ReGUIDE significantly advances web grounding performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-05-21T08:36:18Z)
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory [0.5584627289325719]
  Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses. But their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues. We introduce Mem0, a scalable memory-centric architecture that addresses this issue by dynamically extracting, consolidating, and retrieving salient information from ongoing conversations.
  arXiv  Detail & Related papers  (2025-04-28T01:46:35Z)
• MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework [15.410873298893817]
  We propose Multi-Modal Knowledge-Based Retrieval-Augmented Generation (MMKB-RAG) This framework leverages the inherent knowledge boundaries of models to dynamically generate semantic tags for the retrieval process. Extensive experiments on knowledge-based visual question-answering tasks demonstrate the efficacy of our approach.
  arXiv  Detail & Related papers  (2025-04-14T10:19:47Z)
• Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval [49.669503570350166]
  Generative information retrieval (GenIR) is a promising neural retrieval paradigm that formulates document retrieval as a document identifier (docid) generation task. Existing GenIR models suffer from token-level misalignment, where models trained to predict the next token often fail to capture document-level relevance effectively. We propose direct document relevance optimization (DDRO), which aligns token-level docid generation with document-level relevance estimation through direct optimization via pairwise ranking.
  arXiv  Detail & Related papers  (2025-04-07T15:27:37Z)
• Leveraging Approximate Caching for Faster Retrieval-Augmented Generation [1.3450852784287828]
  Retrieval-augmented generation (RAG) enhances the reliability of large language model (LLM) answers by integrating external knowledge. RAG increases the end-to-end inference time since looking for relevant documents from large vector databases is computationally expensive. We introduce Proximity, an approximate key-value cache that optimize the RAG workflow by leveraging similarities in user queries.
  arXiv  Detail & Related papers  (2025-03-07T15:54:04Z)
• Cross-Format Retrieval-Augmented Generation in XR with LLMs for Context-Aware Maintenance Assistance [6.16808916207942]
  This paper presents a detailed evaluation of a Retrieval-Augmented Generation system that integrates large language models (LLMs) We assess the performance of eight LLMs, emphasizing key metrics such as response speed and accuracy, which were quantified using BLEU and METEOR scores. The results validate the system's ability to deliver timely and accurate responses, highlighting the potential of RAG frameworks to optimize maintenance operations.
  arXiv  Detail & Related papers  (2025-02-21T17:19:39Z)
• QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performance [1.433758865948252]
  This work presents a novel architecture for building Retrieval-Augmented Generation (RAG) systems.<n>RAG architecture is constructed to generate responses from the target document.<n>We introduce QuIM-RAG, a novel approach for the retrieval mechanism in our system.
  arXiv  Detail & Related papers  (2025-01-06T01:07:59Z)
• Improving Factuality with Explicit Working Memory [63.47122478975407]
  Large language models can generate factually inaccurate content, a problem known as hallucination.<n>We introduce EWE (Explicit Working Memory), a novel approach that enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources.
  arXiv  Detail & Related papers  (2024-12-24T00:55:59Z)
• SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval [0.7421845364041001]
  This paper introduces SKETCH, a novel methodology that enhances the RAG retrieval process by integrating semantic text retrieval with knowledge graphs.<n>SKETCH consistently outperforms baseline approaches on key RAGAS metrics such as answer_relevancy, faithfulness, context_precision and context_recall.<n>Results highlight SKETCH's capability in delivering more accurate and contextually relevant responses, setting new benchmarks for future retrieval systems.
  arXiv  Detail & Related papers  (2024-12-19T22:51:56Z)
• LightRAG: Simple and Fast Retrieval-Augmented Generation [12.86888202297654]
  Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources. Existing RAG systems have significant limitations, including reliance on flat data representations and inadequate contextual awareness. We propose LightRAG, which incorporates graph structures into text indexing and retrieval processes.
  arXiv  Detail & Related papers  (2024-10-08T08:00:12Z)
• SFR-RAG: Towards Contextually Faithful LLMs [57.666165819196486]
  Retrieval Augmented Generation (RAG) is a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance. We introduce SFR-RAG, a small LLM that is instruction-textual with an emphasis on context-grounded generation and hallucination. We also present ConBench, a new evaluation framework compiling multiple popular and diverse RAG benchmarks.
  arXiv  Detail & Related papers  (2024-09-16T01:08:18Z)
• Dynamic Data Pruning for Automatic Speech Recognition [58.95758272440217]
  We introduce Dynamic Data Pruning for ASR (DDP-ASR), which offers fine-grained pruning granularities specifically tailored for speech-related datasets. Our experiments show that DDP-ASR can save up to 1.6x training time with negligible performance loss.
  arXiv  Detail & Related papers  (2024-06-26T14:17:36Z)
• RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation [11.321659218769598]
  Retrieval-Augmented Generation (RAG) has shown significant improvements in various natural language processing tasks. RAGCache organizes the intermediate states of retrieved knowledge in a knowledge tree and caches them in the GPU and host memory hierarchy. RAGCache reduces the time to first token (TTTF) by up to 4x and improves the throughput by up to 2.1x compared to vLLM integrated with Faiss.
  arXiv  Detail & Related papers  (2024-04-18T18:32:30Z)
• Synergistic Interplay between Search and Large Language Models for Information Retrieval [141.18083677333848]
  InteR allows RMs to expand knowledge in queries using LLM-generated knowledge collections. InteR achieves overall superior zero-shot retrieval performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-12T11:58:15Z)
• Learning from Context or Names? An Empirical Study on Neural Relation Extraction [112.06614505580501]
  We study the effect of two main information sources in text: textual context and entity mentions (names) We propose an entity-masked contrastive pre-training framework for relation extraction (RE) Our framework can improve the effectiveness and robustness of neural models in different RE scenarios.
  arXiv  Detail & Related papers  (2020-10-05T11:21:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.