Simulating and Evaluating Generative Modeling and Collaborative Filtering in Complex Social Networks

We introduce a multi-agent simulation framework for modeling large-scale online social dynamics by combining retrieval-augmented large language models, generative embedding methods, and collaborative filtering. Our approach learns diverse agent embeddings to capture varying user behaviors and employs a multi-layer perceptron for user-content ranking. We compare three strategies-(1) a generative modeling approach that integrates agent embeddings and collaborative filtering, (2) an LLM-based method grounded in historical context, and (3) a reflection-based clustering technique-and evaluate them on metrics such as comment volume, tree depth, user engagement patterns, and topic distribution. Results show that generative embeddings coupled with collaborative filtering better approximate complex phenomena like localized influencers, specialized subcommunities, and emergent echo chambers. Moreover, our framework supports policy-driven experimentation by incorporating social regularizers (cohesion, polarization, and bias) to simulate scenarios ranging from tightly knit communities to more balanced, cross-cutting interactions. By integrating largescale data with adaptable LLM-driven agents, this work provides a versatile, data-centric foundation for simulating and analyzing online social ecosystems at scale.