2026/05/05 by Jiale Chang, Yuxiang Ren · 1 voice
Computer Science · #Computer data storage #Construct (python library) #Edge device #Episodic memory #Forgetting #Key (lock) #Machine Learning in Healthcare #Multimodal Machine Learning Applications #Overlay #Semantic memory #Topic Modeling #cs.AI
paper · pdf · doi:10.48550/arxiv.2605.03804
openalex publication_date 2026/05/05 · arxiv published 2026/05/05 · openalex created_date 2026/05/07 · arxiv updated 2026/05/25 · openalex updated_date 2026/07/28
Long-term personalized memory for LLM agents is challenging on resource-limited edge devices due to high storage costs and multimodal complexity. To address this, we propose ScrapMem, a framework that integrates multimodal data into "Scrapbook Page." ScrapMem introduces Optical Forgetting, an optical compression mechanism that progressively reduces the resolution of older memories, lowering storage cost while suppressing low-value details. To maintain semantic consistency, we construct an Episodic Memory Graph (EM-Graph) that organizes key events into a causal-temporal structure. Extensive experiments on the multimodal ATM-Bench showcase that ScrapMem provides three main benefits: (1) strong performance, achieving a new state-of-the-art with a 51.0% Joint@10 score; (2) high storage efficiency, reducing memory usage by up to 93% via optical forgetting; and (3) improved recall, increasing Recall@10 to 70.3% through structured aggregation. ScrapMem offers an effective and storage-efficient solution for on-device long-term memory in multimodal LLM agents.