PolyMemDB：一款面向AI记忆管理的多语言数据库系统
PolyMemDB: A Polyglot Database System for AI Memory Management
浏览论文内容
中文总结 AI 辅助
针对现有智能体记忆系统的存储碎片化与事实冲突问题，推出PolyMemDB多语言数据库系统，通过多语言存储架构与概率推理引擎管理智能体记忆，以减少LLM幻觉并提升个性化体验。
中文摘要 AI 辅助
随着个人智能体的广泛应用，用户在长期交互过程中会产生大量异构数据。将这些数据作为长期记忆加以利用，有助于减少token开销并提供个性化体验。然而，现有的记忆系统存在两大主要局限：它们依赖单一存储范式，导致多维数据碎片化；且缺乏细粒度的数据溯源能力，无法解决长期事实冲突，进而加剧大语言模型（LLM）的幻觉问题。在本演示中，我们推出PolyMemDB，一款专为管理智能体记忆设计的新型系统。PolyMemDB采用多语言存储架构，用于跟踪和管理各类记忆类型，包括图数据、向量数据、概率数据及时空数据。为确保事实一致性并减少幻觉，它配备了概率推理引擎，该引擎将时间衰减与半环聚合相结合，可解决长期事实冲突，提供详细的数据溯源信息，并使用户能够透明地追踪推理链。
英文摘要
With the widespread adoption of personal intelligent agents, users generate massive, heterogeneous data during long-term interactions. Leveraging this data as long-term memory helps reduce token overhead and deliver personalized experiences. However, existing memory systems face two primary limitations: they rely on single-storage paradigms that fragment multi-dimensional data, and they lack fine-grained data provenance to resolve long-term factual conflicts, thereby worsening LLM hallucinations. In this demonstration, we introduce PolyMemDB, a novel system tailored for managing agent memory. PolyMemDB has a polyglot storage architecture designed to track and manage various memory types, including graph, vector, probability and spatial-temporal data. To ensure factual consistency and reduce hallucinations, it features a probabilistic inference engine that integrates temporal decay with semiring aggregation, resolving long-term factual conflicts, providing detailed data provenance, and enabling users to trace reasoning chains transparently.
发表机构
- University of Helsinki（赫尔辛基大学）
机构由 AI 辅助整理，请以论文原文为准。
