超越静态测试平台：面向动态推荐系统的交互中心智能体模拟平台
Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems
AI总结：
针对推荐系统评估中静态测试平台的不足，提出交互中心智能体模拟平台RecInter，通过用户行为动态更新物品属性及商家智能体回复，实现高保真模拟，并复现品牌忠诚和马太效应等涌现现象。
摘要：
评估和迭代推荐系统至关重要，然而传统的A/B测试资源消耗大，离线方法难以应对动态的用户-平台交互。虽然基于智能体的模拟前景广阔，但现有平台往往缺乏用户行为动态重塑环境的机制。为弥补这一空白，我们提出了RecInter，一个新颖的基于智能体的推荐系统模拟平台，具备稳健的交互机制。在RecInter平台中，模拟用户行为（如点赞、评论、购买）实时动态更新物品属性，引入的商家智能体（Merchant Agents）能够回复，从而营造更真实、不断演化的生态系统。通过多维用户画像模块（Multidimensional User Profiling）、先进智能体架构（Advanced Agent Architecture）以及基于思维链（Chain-of-Thought, CoT）增强交互数据微调的大语言模型（LLM），确保了高保真模拟。我们的平台显著提升了模拟可信度，并成功复现了品牌忠诚度（Brand Loyalty）和马太效应（Matthew Effect）等涌现现象。实验表明，该交互机制对于模拟真实系统演化至关重要，使我们的平台成为推荐系统研究的可信测试平台。我们的代码可在https://github.com/jinsong8/RecInter获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
