Distributed multi-agent systems use large language models to enable collaborative intelligence while preserving privacy, yet systematic evaluations of long-term memory under network constraints remain limited. This study presents a flexible testbed comparing 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 that mem0 significantly outperforms Graphiti in efficiency, with faster loading times, lower resource consumption, and minimal network overhead, while accuracy differences are not statistically significant. Applying a statistical pareto efficiency framework, mem0 is identified as the optimal choice that balances cost and accuracy in DMAS.

翻译：分布式多智能体系统利用大语言模型实现协同智能并保护隐私，但在网络约束下对长期记忆的系统性评估仍较为有限。本研究提出了一个灵活测试平台，基于LOCOMO长上下文基准，对向量记忆框架mem0和图知识图谱Graphiti进行比较。实验在无约束和约束网络条件下进行，测量了计算、财务和精度指标。结果表明，mem0在效率上显著优于Graphiti，具有更快的加载速度、更低的资源消耗和最小的网络开销，而精度差异未达到统计学显著性。通过应用统计帕累托效率框架，本研究确定mem0是在分布式多智能体系统中平衡成本与精度的最优选择。