Evaluating Memory Capability in Continuous Lifelog Scenario
For researchers developing memory-augmented AI systems, this benchmark and evaluation protocol reveal that over-designed structures and lossy compression are detrimental in lifelog scenarios, challenging existing assumptions.
The paper introduces LifeDialBench, a benchmark for evaluating memory systems in continuous lifelog scenarios, and proposes an online evaluation protocol. Experiments show that current sophisticated memory systems fail to outperform a simple RAG-based baseline, highlighting the need for high-fidelity context preservation.
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.