Skip to content
arXiv Game AI· Chloe Su·· 2026-10-16PickAI score45

Chloe Su proposes MFM multimodal filesystem memory architecture, outperforming baselines on long-horizon embodied agent tasks

Multimodal Filesystem Memory For Long-Horizon Embodied Agents

AI summary

The paper proposes MFM, a multimodal filesystem memory architecture that stores episodic, spatial, semantic and procedural, and working memory separately, and links these representations to the underlying multimodal segments through retrievable text records, so that an agent can use contextual cues to find past experiences and revisit the original observations to recover details missing from the text descriptions.

Why it matters

The paper lays out the design of layered memory plus text retrieval linked back to the original segments, and compares three base models on Minecraft and computer-operation tasks.

Source: arXiv Game AI · arxiv.org