DecisionRAG：不用检索器，用决策模型在文档树中导航检索
Retriever-Free Retrieval: Navigating Documents with Decision Models
这论文思路挺妙：检索不靠相似度匹配，让语言模型像逛图书馆一样逐层判断该往哪走，还能零训练超过 8B 重排器。
DecisionRAG 提出让预训练语言模型直接参与检索：模型在单次前向传播中同时评估多个候选分支，不生成任何 token，像人在图书馆里从大类主题逐层浏览到具体段落。它不需要任务特定训练，也不需要第一阶段检索器。在 MultiDoc2Dial 上比配备 8B 重排序器的稠密检索高出 13.8 R@1，在 Natural Questions 上高出 17.4 Hit@1。在包含 268 万 Wikipedia 段落语料在内的四个基准上，单次查询检索耗时仅 0.7-1.8 秒。
Retriever-Free Retrieval: Navigating Documents with Decision Models
While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single forward pass, without generating any tokens, and show that judging candidates in a shared context makes their relevance estimates comparable. Like a person browsing a library, DecisionRAG navigates the corpus's inherent structure from broad topics down to individual passages, deciding at each level which branches are worth exploring. Without task-specific training or a first-stage retriever, DecisionRAG outperforms dense retrieval with an 8B reranker by 13.8 R@1 points on MultiDoc2Dial and 17.4 Hit@1 points on Natural Questions. Across four benchmarks, including a corpus of 2.68 million Wikipedia paragraphs, retrieval takes just 0.7-1.8 seconds per query.