arXiv:2607.09759v1 Announce Type: new Abstract: Building assistants that can continually watch the world, remember what they see, and reason over their accumulated experience is a long-standing goal, and recently multimodal agents equipped with long-term memory over video streams have attracted inc

中文全文翻译正在补齐，可先查看下方英文原文。

[Submitted on 6 Jul 2026 (

v1

), last revised 14 Jul 2026 (this version, v2)]

Title:ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams

View a PDF of the paper titled ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams, by Xiaokang Ma and 8 other authors

View PDF HTML (experimental)

Abstract:Building assistants that can continually watch the world, remember what they see, and reason over their accumulated experience is a long-standing goal, and recently multimodal agents equipped with long-term memory over video streams have attracted increasing interest. Unfortunately, existing systems either keep their memory inside the model context or in a flat feature store, and organize it around frames rather than around the persistent entities a stream is really about, which confines them to bounded videos and weakens their ability to track who and what reappears over time. In this paper, we propose ReflectWorld-MM, an entity-oriented multimodal memory system for open-ended video streams. It consists of three parts. The first is a perception front-end that turns an audiovisual stream into entity-resolved observations under a bounded short-term memory. The second is a hierarchical long-term memory, grounded in human memory theory, that couples a multi-scale episodic memory, an evolving entity-centric semantic memory, and a procedural memory. The third is a complete realization, built for real-world operation, that ingests arbitrary streams and plugs into off-the-shelf assistants. Across six long-video and lifelong-memory benchmarks, ReflectWorld-MM achieves the best accuracy on all six, outperforming strong memory agents and a frontier model.

Submission history

From: Jie Gu [

view email

]

[v1]

Mon, 6 Jul 2026 13:17:53 UTC (10,240 KB)

[v2]

Tue, 14 Jul 2026 07:18:26 UTC (10,240 KB)