Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems
This provides a more realistic testbed for recommender systems research, addressing a bottleneck in dynamic evaluation methods.
The authors tackled the problem of evaluating recommender systems by introducing RecInter, an agent-based simulation platform that features dynamic user-platform interactions where user actions update item attributes in real-time, achieving significantly improved simulation credibility and replicating emergent phenomena like Brand Loyalty and the Matthew Effect.
Evaluating and iterating upon recommender systems is crucial, yet traditional A/B testing is resource-intensive, and offline methods struggle with dynamic user-platform interactions. While agent-based simulation is promising, existing platforms often lack a mechanism for user actions to dynamically reshape the environment. To bridge this gap, we introduce RecInter, a novel agent-based simulation platform for recommender systems featuring a robust interaction mechanism. In RecInter platform, simulated user actions (e.g., likes, reviews, purchases) dynamically update item attributes in real-time, and introduced Merchant Agents can reply, fostering a more realistic and evolving ecosystem. High-fidelity simulation is ensured through Multidimensional User Profiling module, Advanced Agent Architecture, and LLM fine-tuned on Chain-of-Thought (CoT) enriched interaction data. Our platform achieves significantly improved simulation credibility and successfully replicates emergent phenomena like Brand Loyalty and the Matthew Effect. Experiments demonstrate that this interaction mechanism is pivotal for simulating realistic system evolution, establishing our platform as a credible testbed for recommender systems research. Our codes are available at https://github.com/jinsong8/RecInter.