Large language models (LLMs) are promising backbones for generative recommender systems, yet a key challenge remains underexplored: verbalization, i.e., converting structured user interaction logs into effective natural language inputs. Existing methods rely on rigid templates that simply concatenate fields, yielding suboptimal representations for recommendation. We propose a data-centric framework that learns verbalization for LLM-based recommendation. Using reinforcement learning, a verbalization agent transforms raw interaction histories into optimized textual contexts, with recommendation accuracy as the training signal. This agent learns to filter noise, incorporate relevant metadata, and reorganize information to improve downstream predictions. Experiments on a large-scale industrial streaming dataset show that learned verbalization delivers up to 93% relative improvement in discovery item recommendation accuracy over template-based baselines. Further analysis reveals emergent strategies such as user interest summarization, noise removal, and syntax normalization, offering insights into effective context construction for LLM-based recommender systems.

翻译：大型语言模型（LLM）作为生成式推荐系统的骨干网络展现出巨大潜力，然而一个关键挑战仍未得到充分探索：言语化，即将结构化的用户交互日志转化为有效的自然语言输入。现有方法依赖于简单拼接字段的固定模板，导致推荐表示效果欠佳。我们提出一种以数据为中心的框架，用于学习基于LLM的推荐系统的言语化表达。通过强化学习，言语化代理将原始交互历史转化为优化的文本上下文，并以推荐准确性作为训练信号。该代理学会过滤噪声、整合相关元数据并重组信息以提升下游预测性能。在大规模工业流式数据集上的实验表明，学习得到的言语化表达在发现项推荐准确率上比基于模板的基线方法获得最高93%的相对提升。进一步分析揭示了用户兴趣摘要、噪声消除和句法规范化等涌现策略，为基于LLM的推荐系统提供了有效上下文构建的洞见。