Graph structures are increasingly used in dialog memory systems, but empirical findings on their effectiveness remain inconsistent, making it unclear which design choices truly matter. We present an experimental, system-oriented analysis of long-term dialog memory architectures. We introduce a unified framework that decomposes dialog memory systems into core components and supports both graph-based and non-graph approaches. Under this framework, we conduct controlled, stage-wise experiments on LongMemEval and HaluMem, comparing common design choices in memory representation, organization, maintenance, and retrieval. Our results show that many performance differences are driven by foundational system settings rather than specific architectural innovations. Based on these findings, we identify stable and reliable strong baselines for future dialog memory research.

翻译：图结构在对话记忆系统中日益普及，但其有效性的实证研究结果仍存在矛盾，使得何种设计选择真正关键尚不明确。本文对长期对话记忆架构进行了实验性、系统导向的分析。我们提出了一个统一框架，将对话记忆系统分解为核心组件，并同时支持基于图与非图的方法。在此框架下，我们在LongMemEval和HaluMem数据集上进行了分阶段对照实验，比较了记忆表示、组织、维护与检索中常见的设计选择。结果表明，许多性能差异源于基础系统设置，而非特定的架构创新。基于这些发现，我们为未来对话记忆研究确立了稳定可靠的强基线模型。