# ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting Source: [ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting]() Collection index: [llms.txt]() Data updated: 2026-05-27T05:00:21.000Z Authors: Jiale Chang, Yuxiang Ren Published: 2026-05-05T14:30:30.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Long-term Memory Question Answering on ATM-Bench 1.0 (test)](): Long-term Memory Question Answering; ATM-Bench 1.0 (test); QS: 52.5. ## Original sources and implementation [Original paper]() [PDF]()