AI搜文档像挑菜？新方法看整篮子
现在的AI搜文档，就像只看单个菜新不新鲜，不管整篮子菜搭不搭——可能全是重复的、互相矛盾的。这篇论文发现，即使最好的排序方法，选出的文档集覆盖关键信息也不到45%。他们搞了个新方法，不训练模型，而是用一套评分标准（像厨师列菜单）直接指导AI选文档，结果用更少的文档和搜索次数，生成的内容反而更好。它不是你明天能用上的，但告诉你：AI搜索的下一个战场，不是找单个好文档，而是组一桌好菜。
📄 原文摘要(英文)
As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evaluation systems remain confined to scoring documents independently and aggregating via nDCG, ignoring inter-document interactions (redundancy, conflict, complementarity) and unable to answer what makes one document set better than another. To address these issues, we propose a complete evaluate-diagnose-optimize framework. We design SetwiseEvalKit, a three-level, nine-dimension document set evaluation benchmark covering both short-form and long-form scenarios, comprising approximately 28K high-quality evaluation rubrics. We systematically evaluate 12 rerankers: even the best method achieves no more than 45% coverage, cross-document coordination dimensions are universally weak, and no single method maintains top performance across both settings. Building on this, we propose Rubric4Setwise, a training-free method that converts rubric-based evaluation criteria into document set selection signals, achieving the best downstream generation performance with fewer documents and search rounds. It is the only method that maintains state-of-the-art results across both scenarios, validating the effectiveness of closing the loop from evaluation to optimization.