GGBond: Growing Graph-Based AI-Agent Society for Socially-Aware Recommender Simulation
Hailin Zhong, Hanlin Wang, Yujun Ye, Meiyi Zhang, Shengxin Zhu
TL;DR
GGBond addresses the limitation of static, short-horizon data in recommender evaluation by introducing a high-fidelity platform that simulates cognitively realistic agents and a dynamic, multi-layer social graph. The approach combines a five-module cognitive architecture with an IC2 motivational engine and a heterogeneous GGBond Graph to model memory, affect, preferences, trust, and social influence, enabling long-term evaluation of recommendation interventions. Key contributions include structure-driven personality inference, multi-layer homophily modeling, LLM-based language reasoning for explainable outputs, and extensive longitudinal evaluation of long-term effects on preference drift and social propagation across representative recommender algorithms. The framework offers a controlled environment for studying social impact, trust dynamics, and causal effects in recommender systems, with potential implications for fairness, robustness, and policy design in real-world deployments.
Abstract
Current personalized recommender systems predominantly rely on static offline data for algorithm design and evaluation, significantly limiting their ability to capture long-term user preference evolution and social influence dynamics in real-world scenarios. To address this fundamental challenge, we propose a high-fidelity social simulation platform integrating human-like cognitive agents and dynamic social interactions to realistically simulate user behavior evolution under recommendation interventions. Specifically, the system comprises a population of Sim-User Agents, each equipped with a five-layer cognitive architecture that encapsulates key psychological mechanisms, including episodic memory, affective state transitions, adaptive preference learning, and dynamic trust-risk assessments. In particular, we innovatively introduce the Intimacy--Curiosity--Reciprocity--Risk (ICR2) motivational engine grounded in psychological and sociological theories, enabling more realistic user decision-making processes. Furthermore, we construct a multilayer heterogeneous social graph (GGBond Graph) supporting dynamic relational evolution, effectively modeling users' evolving social ties and trust dynamics based on interest similarity, personality alignment, and structural homophily. During system operation, agents autonomously respond to recommendations generated by typical recommender algorithms (e.g., Matrix Factorization, MultVAE, LightGCN), deciding whether to consume, rate, and share content while dynamically updating their internal states and social connections, thereby forming a stable, multi-round feedback loop. This innovative design transcends the limitations of traditional static datasets, providing a controlled, observable environment for evaluating long-term recommender effects.