Distributed multi-agent systems (DMAS) based on large language models (LLMs) enable collaborative intelligence while preserving data privacy. However, systematic evaluations of long-term memory under network constraints are limited. This study introduces a flexible testbed to compare mem0, a vector-based memory framework, and Graphiti, a graph-based knowledge graph, using the LoCoMo long-context benchmark. Experiments were conducted under unconstrained and constrained network conditions, measuring computational, financial, and accuracy metrics. Results indicate mem0 significantly outperforms Graphiti in efficiency, featuring faster loading times, lower resource consumption, and minimal network overhead. Crucially, accuracy differences were not statistically significant. Applying a statistical Pareto efficiency framework, mem0 is identified as the optimal choice, balancing cost and accuracy in DMAS.

翻译：基于大语言模型（LLMs）的分布式多智能体系统（DMAS）能够在保护数据隐私的前提下实现协同智能。然而，现有研究对网络约束下长期记忆机制的系统性评估仍显不足。本研究引入了一个灵活测试平台，利用LoCoMo长上下文基准，对基于向量的记忆框架mem0与基于图结构的知识图谱Graphiti进行对比分析。实验在无约束与受约束网络条件下展开，测量了计算成本、经济成本及精度指标。结果表明，mem0在效率方面显著优于Graphiti，其加载速度更快、资源消耗更低且网络开销极小。关键发现是，两者的精度差异未达到统计学显著性。通过统计帕累托效率框架分析，mem0被确认为平衡DMAS成本与精度的最优选择。