Nowadays, wearable devices can continuously lifelog ambient conversations, creating substantial opportunities for memory systems. However, existing benchmarks primarily focus on online one-on-one chatting or human-AI interactions, thus neglecting the unique demands of real-world scenarios. Given the scarcity of public lifelogging audio datasets, we propose a hierarchical synthesis framework to curate \textbf{\textsc{LifeDialBench}}, a novel benchmark comprising two complementary subsets: \textbf{EgoMem}, built on real-world egocentric videos, and \textbf{LifeMem}, constructed using simulated virtual community. Crucially, to address the issue of temporal leakage in traditional offline settings, we propose an \textbf{Online Evaluation} protocol that strictly adheres to temporal causality, ensuring systems are evaluated in a realistic streaming fashion. Our experimental results reveal a counterintuitive finding: current sophisticated memory systems fail to outperform a simple RAG-based baseline. This highlights the detrimental impact of over-designed structures and lossy compression in current approaches, emphasizing the necessity of high-fidelity context preservation for lifelog scenarios.
@article{arxiv.2604.11182,
title = {Evaluating Memory Capability in Continuous Lifelog Scenario},
author = {Jianjie Zheng and Zhichen Liu and Zhanyu Shen and Jingxiang Qu and Guanhua Chen and Yile Wang and Yang Xu and Yang Liu and Sijie Cheng},
journal= {arXiv preprint arXiv:2604.11182},
year = {2026}
}