利用智能体搜索轨迹优化稠密检索器，无需标注即可提升检索效果。
Navigation-Informed Embeddings: Dense-Retriever Adaptation from Agent Search Traces
- 基于搜索轨迹设计新目标函数，用停止文档和路径文档构建对比学习信号。
- 在独立测试集上召回率从72.2提升至78.0，长路径场景下性能提升显著。
- 适用于已有搜索轨迹的部署场景，零额外标注成本，适合生产环境微调。
智能体检索流程会生成查询、检索和停止的轨迹记录。本文研究如何利用这些轨迹，在无需新相关性标签、合成查询或大模型判断的情况下，适应已部署的稠密检索器以应对工作流分布变化。提出导航感知嵌入（NIE），包括两种轨迹衍生的目标：NIE-Stop将停止文档作为软正例；NIE-Path额外使用前序路径文档作为硬负例，并施加几何衰减的序数约束。基于保留源轨迹训练的BGE编码器，在独立目标基准上的Recall@20从72.2提升至78.0。NIE-Stop整体达76.9，长路径达52.3；NIE-Path进一步将长路径性能提升至55.4，远超未适配编码器的46.7。随机打乱顺序的对照组损失3.2分。在无公开基准训练的前提下，相同适配器也使BEIR HotpotQA的nDCG@10提升1.9分。NIE为已有轨迹留存的场景提供轻量级、零标注成本的适应通道。
原文摘要 · Abstract (English)
Agentic retrieval workflows produce query, retrieval, and stopping traces as a byproduct of answering questions. We study how these traces can adapt a deployed dense retriever to changing workflow distributions without new relevance labels, synthetic queries, or LLM judgments. We introduce Navigation-Informed Embeddings (NIE), a family of trace-derived objectives. NIE-Stop turns the stopping document into a soft positive; NIE-Path additionally uses preceding path documents as hard comparisons and imposes ordinal constraints with geometric decay. A BGE encoder adapted from retained source trajectories improves support Recall@20 on an independent target benchmark from 72.2 to 78.0 overall. NIE-Stop reaches 76.9 overall and 52.3 on long paths; NIE-Path raises long-path performance to 55.4, compared with 46.7 for the unadapted encoder. A shuffled-order control under the full path objective loses 3.2 points. Without public-benchmark training, the same adapter also improves nDCG@10 by 1.9 points on standard BEIR HotpotQA. NIE therefore provides a lightweight adaptation channel for settings where trajectories are already retained, with zero incremental labeling cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。