We present PushGen, an automated framework for generating high-quality push notifications comparable to human-crafted content. With the rise of generative models, there is growing interest in leveraging LLMs for push content generation. Although LLMs make content generation straightforward and cost-effective, maintaining stylistic control and reliable quality assessment remains challenging, as both directly impact user engagement. To address these issues, PushGen combines two key components: (1) a controllable category prompt technique to guide LLM outputs toward desired styles, and (2) a reward model that ranks and selects generated candidates. Extensive offline and online experiments demonstrate its effectiveness, which has been deployed in large-scale industrial applications, serving hundreds of millions of users daily.
@article{arxiv.2512.14490,
title = {PushGen: Push Notifications Generation with LLM},
author = {Shifu Bie and Jiangxia Cao and Zixiao Luo and Yichuan Zou and Lei Liang and Lu Zhang and Linxun Chen and Zhaojie Liu and Xuanping Li and Guorui Zhou and Kaiqiao Zhan and Kun Gai},
journal= {arXiv preprint arXiv:2512.14490},
year = {2025}
}