VikingMem: A Memory Base Management System for Stateful LLM-based Applications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fu, Jiajie, Chen, Junwen, Wang, Mengzhao, He, Aoxiang, Sheng, Maojia, Ke, Xiangyu, Zhu, Yifan, Gao, Yunjun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910271379865600
author Fu, Jiajie
Chen, Junwen
Wang, Mengzhao
He, Aoxiang
Sheng, Maojia
Ke, Xiangyu
Zhu, Yifan
Gao, Yunjun
author_facet Fu, Jiajie
Chen, Junwen
Wang, Mengzhao
He, Aoxiang
Sheng, Maojia
Ke, Xiangyu
Zhu, Yifan
Gao, Yunjun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29640
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VikingMem: A Memory Base Management System for Stateful LLM-based Applications
Fu, Jiajie
Chen, Junwen
Wang, Mengzhao
He, Aoxiang
Sheng, Maojia
Ke, Xiangyu
Zhu, Yifan
Gao, Yunjun
Artificial Intelligence
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.
title VikingMem: A Memory Base Management System for Stateful LLM-based Applications
topic Artificial Intelligence
url https://arxiv.org/abs/2605.29640