Traditional recommendation systems tend to trap users in strong feedback loops by excessively pushing content aligned with their historical preferences, thereby limiting exploration opportunities and causing content fatigue. Although large language models (LLMs) demonstrate potential with their diverse content generation capabilities, existing LLM-enhanced dual-model frameworks face two major limitations: first, they overlook long-term preferences driven by group identity, leading to biased interest modeling; second, they suffer from static optimization flaws, as a one-time alignment process fails to leverage incremental user data for closed-loop optimization. To address these challenges, we propose the Co-Evolutionary Alignment (CoEA) method. For interest modeling bias, we introduce Dual-Stable Interest Exploration (DSIE) module, jointly modeling long-term group identity and short-term individual interests through parallel processing of behavioral sequences. For static optimization limitations, we design a Periodic Collaborative Optimization (PCO) mechanism. This mechanism regularly conducts preference verification on incremental data using the Relevance LLM, then guides the Novelty LLM to perform fine-tuning based on the verification results, and subsequently feeds back the output of the continually fine-tuned Novelty LLM to the Relevance LLM for re-evaluation, thereby achieving a dynamic closed-loop optimization. Extensive online and offline experiments verify the effectiveness of the CoEA model in serendipitous recommendation.

翻译：传统推荐系统倾向于通过过度推送符合用户历史偏好的内容，将用户困于强反馈循环中，从而限制探索机会并导致内容疲劳。尽管大型语言模型（LLM）凭借其多样化的内容生成能力展现出潜力，但现有的LLM增强双模型框架面临两大局限：首先，它们忽视了由群体身份驱动的长期偏好，导致兴趣建模存在偏差；其次，它们存在静态优化缺陷，因为一次性对齐过程无法利用增量用户数据进行闭环优化。为应对这些挑战，我们提出了协同进化对齐（CoEA）方法。针对兴趣建模偏差，我们引入了双稳态兴趣探索（DSIE）模块，通过对行为序列的并行处理，联合建模长期群体身份与短期个体兴趣。针对静态优化局限，我们设计了一种周期性协同优化（PCO）机制。该机制定期使用相关性LLM对增量数据进行偏好验证，随后引导新颖性LLM基于验证结果进行微调，并将持续微调后的新颖性LLM输出反馈至相关性LLM进行重新评估，从而实现动态闭环优化。大量的线上与线下实验验证了CoEA模型在惊喜推荐中的有效性。