1
PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models
整页优化新框架PageLLM，用多粒度奖励机制让大语言模型精准调控页面布局与内容，显著提升用户体验。
arXiv:2506.09084v2 Announce Type: replace-cross Abstract: Whole-page optimization (WPO) decides how search and recommendation results are surfaced to …