VikingMem:面向有状态LLM应用的记忆库管理系统
VikingMem: A Memory Base Management System for Stateful LLM-based Applications
AI总结:
提出记忆库(Memory Base)数据管理范式,并基于VikingDB向量引擎实现VikingMem系统,通过事件与实体抽象、主题时间线压缩和时间加权召回,在长期记忆基准上提升检索效果达30%。
摘要:
大型语言模型彻底改变了交互式应用;然而,其有限的上下文窗口为维护有状态的长期交互带来了关键的数据管理挑战。现有的记忆方法通常依赖于简单的提取方法,导致记忆不完整,或使用针对单一用例(如聊天机器人)的刚性、单用途记忆提取提示。因此,它们缺乏泛化能力,在多样化的下游任务中表现不佳。为弥补这一差距,我们引入了记忆库(Memory Base),一种用于管理长期交互持久状态的新型数据管理范式。其特点包括三个核心原则:从原始信息流中选择性提取高价值记忆;固有的状态性和演化性,其中记忆内容被逐步总结、纠正并按时间加权以优先处理近期交互;以及一种可泛化的抽象范式,旨在跨不同应用(包括教育、推荐和智能体记忆)实现稳健的可迁移性。基于此,我们提出了VikingMem,一个在VikingDB向量引擎上实现的端到端记忆库管理系统。VikingMem通过互连的事件和实体抽象具体化了这一范式。它采用以事件为中心的记忆提取来选择性处理复杂信息流,同时实体由事件动态更新以实现有状态演化。通过基于主题时间线的时间压缩和时间加权召回,系统逐步生成高层级总结记忆,优先处理近期项目,并压缩和淡出较旧项目。在长期记忆基准上的广泛评估表明,VikingMem在记忆检索效果上比基线方法提升高达30%,同时保持了交互应用所需的低延迟。
英文摘要:
Large Language Models have revolutionized interactive applications; however, their finite context windows pose a critical data management challenge for maintaining stateful, long-term interactions. Existing memory approaches often rely on simplistic extraction methods that lead to incomplete memories or use rigid, single-purpose memory extraction prompts tailored to a single use case, such as chatbots. Consequently, they lack generalizability and perform poorly across diverse downstream tasks. To bridge this gap, we introduce the Memory Base, a novel data management paradigm for managing the persistent state of long-term interactions. It is characterized by three core principles: selective extraction of high-value memories from raw information streams; inherent statefulness and evolution, where memory content is progressively summarized, corrected, and temporally weighted to prioritize recent interactions; and a generalizable abstraction paradigm designed for robust transferability across diverse applications, including education, recommendation, and agent memory. Building on this foundation, we present VikingMem, an end-to-end Memory Base Management System implemented on the VikingDB vector engine. VikingMem materializes this paradigm through interconnected event and entity abstractions. It features event-centric memory extraction to selectively handle complex information streams, while entities are dynamically updated by events to achieve stateful evolution. Using temporal compression via a topic-wise timeline and time-weighted recall, the system progressively produces high-level summary memories, prioritizes recent items, and compresses and fades older ones. Extensive evaluations on long-term memory benchmarks demonstrate that VikingMem outperformes baselines by up to 30% in memory retrieval effectiveness while maintaining the low latency essential for interactive applications.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。