Metis: Memory Foundation Model
- 类型:arxiv
- 标识:2607.26760
- 链接:http://arxiv.org/abs/2607.26760v1
- 主分类:agent
- 形态:method
- 被引:1
- 被引来源:Semantic Scholar
- S2被引:1
- OpenAlex被引:0
- 影响力被引:0
- TLDR:This paper proposes Metis, the first prototype of memory foundation models, which empower foundation models with native memory capabilities and shows that native memory offers advantages in architecture, end-to-end optimization, and efficiency.
- OpenAlex ID:W7171857741
- OpenAlex DOI:10.48550/arxiv.2607.26760
- DOI:10.48550/arxiv.2607.26760
- DOI来源:OpenAlex
- 开放获取:green
- 开放获取链接:https://doi.org/10.48550/arxiv.2607.26760
- OpenAlex更新:2026-08-25
- 待LLM分类:否
- 标题中文:Metis: 记忆基础模型
- TLDR中文:本文提出 Metis,首个 memory foundation model 原型,赋予 foundation model 原生记忆能力,并表明原生记忆在架构、端到端优化和效率方面具有优势。
- 来源文件:
- /inbox/tom/_candidates/2026-07-30-agent-rag-longcontext-candidates.json
- /inbox/tom/_candidates/2026-07-31-agent-rag-longcontext-candidates.json
- [S2 enrich]
- [OpenAlex backfill]