# Metis: Memory Foundation Model

Page: https://stenobird.com/podcast/daily-paper-cast-7079649/metis-memory-foundation-model
Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/metis-memory-foundation-model.md
Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649)
Published: 2026-08-01T04:37:33+00:00
Episode link: https://share.transistor.fm/s/22649fde
Audio file: https://media.transistor.fm/22649fde/60a2f0b6.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/metis-memory-foundation-model
Duration seconds: 1113

## Resource

🤗 Upvotes: 245 | cs.CL, cs.LG Authors: Zeyu Zhang, Ziliang Guo, Yihang Sun, Xichong Zhang, Xixuan Hao, Zehao Lin, Yang Zhang, Xiaoyan Zhao, Tong Shen, Bo Tang, Zhi-Qin John Xu, Junchi Yan, Haofen Wang, Xu Chen, Feiyu Xiong, Zhiyu Li, Tat-Seng Chua Title: Metis: Memory Foundation Model Arxiv: http://arxiv.org/abs/2607.26760v1 Abstract: Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal foundation models and large reasoning models. However, agent memory is still primarily implemented through external modules, leaving the native memory capability largely unexplored. In this paper, we take a first step toward this direction by introducing memory foundation models, which empower foundation models with native memory capabilities. We formalize native memory from two perspectives: a persistent and dynamically evolving memory state within the backbone, and native memory procedures that autonomously store and utilize information through model computation. We show that native memory offers advantages in architecture, end-to-end optimization, and efficiency. Based on this formulation, we propose Metis, the first prototype of memory foundation models. Metis introduces a new architecture that equips a foundation model with a native memory state, allowing historical information to be compressed into the model and accessed through memory attention. We construct large-scale memory-specific training data and introduce multiple optimization objectives to acquire these native memory procedures through mid-training. The online memory maintenance of Metis is gradient-free, and the memory update requires only a forward pass. At inference time, all learned model weights remain frozen, while the nat…

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/metis-memory-foundation-model/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/daily-paper-cast-7079649/metis-memory-foundation-model.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.