Abstract
In e-commerce private-domain channels such as instant messaging and e-mail, merchants engage customers directly as part of their Customer Relationship Management (CRM) programmes to drive retention and conversion. While a few top performers excel at crafting outbound messages, most merchants struggle to write persuasive copy because they lack both expertise and scalable tools. We introduce CRMAgent, a multi-agent system built on large language models (LLMs) that generates high-quality message templates and actionable writing guidance through three complementary modes. First, group-based learning enables the agent to learn from a merchant's own top-performing messages within the same audience segment and rewrite low-performing ones. Second, retrieval-and-adaptation fetches templates that share the same audience segment and exhibit high similarity in voucher type and product category, learns their successful patterns, and adapts them to the current campaign. Third, a rule-based fallback provides a lightweight zero-shot rewrite when no suitable references are available. Extensive experiments show that CRMAgent consistently outperforms merchants' original templates, delivering significant gains in both audience-match and marketing-effectiveness metrics.
Abstract (translated)
在电子商务的私域渠道，如即时通讯和电子邮件中，商家通过客户关系管理（CRM）计划直接与顾客互动，以促进客户的留存率和转化率。尽管一些表现卓越的企业能够制作出有效的外向型消息，但大多数企业却因缺乏专业知识和可扩展工具而难以编写有说服力的文案。为此，我们推出了CRMAgent，这是一个基于大规模语言模型（LLMs）构建的多代理系统，通过三种互补模式生成高质量的消息模板并提供可操作的写作指导。 首先，群体学习模式使代理能够从同一受众细分市场中商家自己表现最好的消息中学习，并改写那些表现较差的信息。其次，检索与适应模式会获取具有相同受众细分、优惠券类型和产品类别相似度高的模板，从中学习成功模式并将其应用于当前的营销活动。第三，基于规则的备用方案在没有合适参考的情况下提供轻量级的一键重写功能。 经过广泛的实验表明，CRMAgent始终能超越商家原有的模板，在与观众匹配度和市场有效性指标方面均取得了显著提升。
URL
https://arxiv.org/abs/2507.08325
