为智能代理设计多模态记忆系统，减少大模型幻觉
PolyMemDB: A Polyglot Database System for AI Memory Management
- 采用多语言存储架构管理图、向量、概率等多维记忆数据
- 通过概率推理引擎实现时间衰减与语义聚合，解决长期事实冲突
- 支持细粒度数据溯源，便于追踪推理链，适合长时交互场景
随着个人智能代理的普及，用户在长期互动中产生大量异构数据。将这些数据作为长期记忆，有助于降低令牌开销并提供个性化体验。然而，现有记忆系统存在两大局限：依赖单一存储范式导致多维数据碎片化，且缺乏细粒度数据溯源能力，难以解决长期事实冲突，加剧大模型幻觉。本文展示PolyMemDB，一种专为代理记忆管理设计的新系统。该系统采用多语言存储架构，可追踪和管理图、向量、概率及时空数据等多种记忆类型。为确保事实一致性、减少幻觉，其配备概率推理引擎，融合时间衰减与半环聚合机制，可有效解决长期事实冲突，提供详细数据溯源，并支持用户透明追溯推理链条。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。