Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.22101 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915309750845440 |
|---|---|
| author | 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 |
| author_facet | 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 |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22101 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models 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 Computation and Language 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. |
| title | MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.22101 |