arXiv:2608. 12627v1 Announce Type: cross Abstract: Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences.
EgoMemReason is a new benchmark for week‑long egocentric video understanding that focuses on memory‑driven reasoning rather than simple perception tasks. It tests three memory types—entity, event, and behavior—across 500 questions, each requiring evidence from an average of 5.1 video segments and 25.9 hours of backtracking. Evaluation of 17 models shows that even the best achieves only 39.6% accuracy, highlighting the difficulty of long‑horizon memory in multimodal systems.
arXiv:2608. 07663v1 Announce Type: cross Abstract: When videos extend from hours to days, directly processing them end-to-end becomes impractical for current Multi-modal Large Language Models (MLLMs).
arXiv:2607. 09759v2 Announce Type: replace-cross 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.
EventMemAgent is an active online video agent that uses a hierarchical memory module to handle continuous perception and long‑range reasoning in streaming video. The framework employs a short‑term memory layer to detect event boundaries and sample frames within a fixed buffer, while a long‑term memory layer archives observations event‑by‑event. It also incorporates a multi‑granular perception toolkit and Agentic Reinforcement Learning to internalize reasoning and tool‑use strategies, achieving competitive results on online video benchmarks.
The paper introduces LatentStream, a progressive latent working memory framework for streaming video understanding that replaces the traditional store‑and‑retrieve paradigm with a retrieve‑and‑internalize approach. It organizes visual history into short, mid, and long‑term levels using Jenks‑guided adaptive consolidation, then expands memory receptive fields to iteratively retrieve and internalize evidence into a compact latent memory. A confidence‑guided optimization further refines this memory, leading to state‑of‑the‑art performance on online and offline video benchmarks.
ICM-Bench is a new benchmark for evaluating identity-centric reasoning in multimodal agents with long-term memory. It consists of 839 synthetic video clips totaling 141 minutes and 1,217 open-ended questions about six recurring adults in a one-year life album. The benchmark isolates the ability to maintain recurring person identities and reason over their cross-time relations, and compares various baseline systems, showing that while Gemini 3.1 Pro performs well overall, its accuracy drops on questions requiring long-term identity profiles.
arXiv:2607. 09759v1 Announce Type: cross 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.
arXiv:2609.21940v1 Announce Type: new Abstract: Long-term memory is essential for large language model (LLM) agents to maintain consistency and personalization over extended interactions. Existing me...
arXiv:2609.08273v1 Announce Type: new Abstract: Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuo...
The paper introduces LatentStream, a progressive latent working memory framework for streaming video understanding. It replaces the traditional store‑and‑retrieve approach with a retrieve‑and‑internalize strategy, organizing visual history into short, mid, and long‑term levels and progressively expanding memory receptive fields to internalize evidence into a compact latent memory. The method also employs confidence‑guided optimization to refine memory tokens, achieving state‑of‑the‑art results on online and offline video benchmarks.
arXiv:2608.30294v1 Announce Type: new Abstract: Streaming video understanding requires answering questions at arbitrary times over a continuously growing visual stream. The central challenge is to co...