The structural properties of naturally arising social graphs are extensively studied to understand their evolution. Prior approaches for modeling network dynamics typically rely on rule-based models, which lack realism and generalizability, or deep learning-based models, which require large-scale training datasets. Social graphs, as abstract graph representations of entity-wise interactions, present an opportunity to explore network evolution mechanisms through realistic simulations of human-item interactions. Leveraging the pre-trained social consensus knowledge embedded in large language models (LLMs), we present GraphAgent-Generator (GAG), a novel simulation-based framework for dynamic, text-attributed social graph generation. GAG simulates the temporal node and edge generation processes for zero-shot social graph generation. The resulting graphs exhibit adherence to seven key macroscopic network properties, achieving an 11% improvement in microscopic graph structure metrics. Through the node classification benchmarking task, we validate GAG effectively captures the intricate text-structure correlations in graph generation. Furthermore, GAG supports generating graphs with up to nearly 100,000 nodes or 10 million edges through large-scale LLM-based agent simulation with parallel acceleration, achieving a minimum speed-up of 90.4%. The source code is available at https://github.com/Ji-Cather/GraphAgent.

翻译：自然形成的社会图的结构特性被广泛研究以理解其演化规律。现有的网络动态建模方法通常依赖于基于规则的模型——这类模型缺乏真实性与泛化能力，或依赖于基于深度学习的模型——这类模型需要大规模训练数据集。社会图作为实体间交互的抽象图表示，为通过模拟真实的人-物交互来探索网络演化机制提供了契机。利用大语言模型（LLMs）中内嵌的预训练社会共识知识，我们提出了GraphAgent-Generator（GAG），一种新颖的、基于模拟的动态文本属性社会图生成框架。GAG模拟了时序节点与边的生成过程，以实现零样本社会图生成。生成的图在七项关键宏观网络特性上表现出良好的符合度，并在微观图结构指标上实现了11%的提升。通过节点分类基准测试任务，我们验证了GAG能够有效捕捉图生成中复杂的文本-结构关联。此外，GAG通过基于大规模LLM的智能体模拟与并行加速，支持生成包含近10万个节点或1000万条边的大规模图，实现了至少90.4%的加速比。源代码发布于 https://github.com/Ji-Cather/GraphAgent。