对比证据路径引导智能体搜索，抑制图连接性排序偏差
原标题：When Connectivity Misleads: Guiding Agentic Search with Contrastive Evidence Paths
AI 摘要
论文提出对比证据路径（CEP）方法，用于缓解图检索中因节点连接度高而导致的排序偏差，并在此基础上构建结构化语料交互（SCI），将候选文档及其连接路径组织为结构化地图，引导搜索智能体验证来源并扩展探索。在 BrowseComp-Plus 和 TREC-COVID 上，SCI 取得最优答案准确率与 nDCG@10，且生成成本最低，相比最强基线工具调用与总生成成本最大降幅分别超过 50% 和 40%。
正文节选
When Connectivity Misleads: Guiding Agentic Search with Contrastive Evidence Paths Abstract. Search agents can use cross-document graphs to discover sources through multi-hop connections and choose subsequent actions based on candidate rankings and relationships within a limited observation window. However, documents may rank highly because their numerous connections make them easier to reach, without necessarily providing more valuable evidence. Graph diffusion methods such as Personalized Page