Year: 2025
Type: preprint
Abstract: Large Language Models (LLMs) have emerged as foundational infrastructure in the pursuit of Artificial General Intelligence (AGI). Despite their remarkable capabilities in language perception and generation, current LLMs fundamentally lack a unified and structured architecture for handling memory. They primarily rely on parametric memory (knowledge encoded in model weights) and ephemeral activation memory (context-limited runtime states). While emerging methods like Retrieval-Augmented Generation (RAG) incorporate plaintext memory, they lack lifecycle management and multi-modal integration, limiting their capacity for long-term knowledge evolution. To address this, we introduce MemOS, a memory operating system designed for LLMs that, for the first time, elevates memory to a first-class operational resource. It builds unified mechanisms for representation, organization, and governance across three core memory types: parametric, activation, and plaintext. At its core is the MemCube, a standardized memory abstraction that enables tracking, fusion, and migration of heterogeneous memory, while offering structured, traceable access across tasks and contexts. MemOS establishes a memory-centric execution framework with strong controllability, adaptability, and evolvability. It fills a critical gap in current LLM infrastructure and lays the groundwork for continual adaptation, personalized intelligence, and cross-platform coordination in next-generation intelligent systems.
Source: arXiv (Cornell University)
Authors: Li, Zhiyu, Song, Shichao, Wang, Hanyu, Niu, Simin, Chen, Ding, Yang, Jiawei, Xi, Chenyang, Lai, Huayi, Zhao, Jihao, Wang, Yezhaohui, Ren, Junpeng, Lin, Zehao, Huo, Jiahao, Chen, Tianyi, Chen, Kai, Li, Kehang, Yin, Zhiqiang, Yu, Qingchen, Tang, Bo, Yang, Hongkang, Xu, Zhi-Qin John, Xiong, Feiyu
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416047871