CARTS：面向推荐文本摘要的协作智能体
CARTS: Collaborative Agents for Recommendation Textual Summarization
AI总结：
本文提出CARTS多智能体大语言模型框架，通过生成增强生成、精炼循环和仲裁三阶段协作生成推荐系统商品标题，实验表明其显著优于单次生成和思维链基线，提升了标题相关性与用户参与度。
摘要：
当前的推荐系统通常需要某种形式的文本数据摘要，例如为商品轮播或其他分组商品展示生成简洁且连贯的标题。尽管大语言模型在自然语言处理领域的文本摘要任务中展现出潜力，但这些方法并不能直接应用于推荐系统，因为推荐系统中的解释必须与商品集合的核心特征高度相关，并严格遵守字数限制。本文提出CARTS（Collaborative Agents for Recommendation Textual Summarization，面向推荐文本摘要的协作智能体），一个专为推荐系统中结构化摘要设计的多智能体大语言模型框架。CARTS将任务分解为三个阶段——生成增强生成（Generation Augmented Generation，GAG）、精炼循环和仲裁，其中连续的智能体角色分别负责提取显著商品特征、基于相关性和长度反馈迭代精炼候选标题，以及通过协作仲裁过程选择最终标题。在大规模电子商务数据和在线A/B测试上的实验表明，CARTS显著优于单次生成和思维链大语言模型基线，实现了更高的标题相关性和更好的用户参与度指标。
英文摘要：
Current recommendation systems often require some form of textual data summarization, such as generating concise and coherent titles for product carousels or other grouped item displays. While large language models have shown promise in NLP domains for textual summarization, these approaches do not directly apply to recommendation systems, where explanations must be highly relevant to the core features of item sets, adhere to strict word limit constraints. In this paper, we propose CARTS (Collaborative Agents for Recommendation Textual Summarization), a multi-agent LLM framework designed for structured summarization in recommendation systems. CARTS decomposes the task into three stages-Generation Augmented Generation (GAG), refinement circle, and arbitration, where successive agent roles are responsible for extracting salient item features, iteratively refining candidate titles based on relevance and length feedback, and selecting the final title through a collaborative arbitration process. Experiments on large-scale e-commerce data and live A/B testing show that CARTS significantly outperforms single-pass and chain-of-thought LLM baselines, delivering higher title relevance and improved user engagement metrics.
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。
