ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams
Summary
ReflectWorld-MM is an entity-oriented multimodal memory system for open-ended video streams, using hierarchical long-term memory inspired by human memory theory, achieving state-of-the-art accuracy on six benchmarks.
View Cached Full Text
Cached at: 07/21/26, 06:35 AM
Paper page - ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams
Source: https://huggingface.co/papers/2607.09759
Abstract
Buildingassistantsthatcancontinuallywatchtheworld,rememberwhattheysee,andreasonovertheiraccumulatedexperienceisalong-standinggoal,andrecentlymultimodalagentsequippedwithlong-termmemoryovervideostreamshaveattractedincreasinginterest.Unfortunately,existingsystemseitherkeeptheirmemoryinsidethemodelcontextorinaflatfeaturestore,andorganizeitaroundframesratherthanaroundthepersistententitiesastreamisreallyabout,whichconfinesthemtoboundedvideosandweakenstheirabilitytotrackwhoandwhatreappearsovertime.Inthispaper,weproposeReflectWorld-MM,anentity-orientedmultimodalmemorysystemforopen-endedvideostreams.Itconsistsofthreeparts.Thefirstisaperceptionfront-endthatturnsanaudiovisualstreamintoentity-resolvedobservationsunderaboundedshort-termmemory.Thesecondisahierarchicallong-termmemory,groundedinhumanmemorytheory,thatcouplesamulti-scaleepisodicmemory,anevolvingentity-centricsemanticmemory,andaproceduralmemory.Thethirdisacompleterealization,builtforreal-worldoperation,thatingestsarbitrarystreamsandplugsintooff-the-shelfassistants.Acrosssixlong-videoandlifelong-memorybenchmarks,ReflectWorld-MMachievesthebestaccuracyonallsix,outperformingstrongmemoryagentsandafrontiermodel.
View arXiv pageView PDFProject pageGitHub68Add to collection
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.09759 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2607.09759 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.09759 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories
MemLife introduces a multimodal memory system for long-term egocentric videos that builds entity-grounded text episodes and retrieves them with a time-indexed agentic reader, improving over training-free baselines by 4.6-12.0% on long-horizon benchmarks. A reinforcement learning framework called MemOpt further optimizes the memory writer for faithfulness and retrievability, yielding consistent 2.7-5.0% gains.
ReWorld: An Interactive World Model with Long-Horizon Memory
ReWorld presents an interactive world model that decouples short-horizon control from long-horizon memory using mixed attention windows and distribution-matching LoRA distillation, enabling real-time video generation with high action fidelity and recall.
RRM: Experience-Driven Reflective Retrieval Memory for Long-Horizon Multimodal Reasoning
This paper introduces Reflective Retrieval Memory (RRM), a memory framework that distills procedural retrieval experience from historical task trajectories to improve evidence retrieval for long-horizon multimodal reasoning. RRM matches or exceeds prior state-of-the-art on M3-Bench-Robot, M3-Bench-Web, and Video-MME-Long benchmarks.
WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
WorldMemArena is a new benchmark with 400 multi-session multimodal tasks for evaluating multimodal agent memory, comparing long-context, RAG, and harness-based memory approaches, revealing that better memory writing does not guarantee better performance and that systems struggle with visual evidence.
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
EM^2Mem proposes an event-centric multimodal memory framework that binds heterogeneous evidence to event anchors for compact, generation-ready memory in long-video question answering, improving accuracy and reducing latency.