GGBond: Growing Graph-Based AI-Agent Society for Socially-Aware Recommender Simulation

2025-05-27

AI Summary

Existing recommender systems rely on static offline datasets, limiting their ability to model long-term user preference evolution and dynamic social influences. Method: We propose the first social-aware recommendation simulation platform, featuring Sim-User agents endowed with a five-layer cognitive architecture and an ICR² motivation engine (Intimacy-Curiosity-Reciprocity-Risk), coupled with a dynamic, multilayer heterogeneous social graph (GGBond Graph) that supports relational evolution. The platform integrates dynamic graph neural networks with mainstream recommendation algorithms (MF, MultVAE, LightGCN) to establish a closed-loop interactive simulation environment. Contribution/Results: It enables observable, intervenable, and continuously feedback-driven evaluation of long-term algorithmic effects and societal impact—overcoming the limitations of static data. By grounding user decision-making in psychological mechanisms and evolving social structures, our platform establishes a novel paradigm for socio-cognitively grounded recommendation modeling.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• Simulate long-term user preference evolution dynamically
• Model social influence in recommender systems realistically
• Integrate psychological mechanisms into agent decision-making processes

Innovation

• Sim-User Agents with five-layer cognitive architecture
• ICR2 motivational engine for decision-making
• GGBond Graph for dynamic social evolution