Retrieval-augmented generation degrades when scaled to large, heterogeneous document collections, where dense similarity loses discriminative power, and top-k retrieval increasingly returns semantically similar but contextually incorrect chunks. We refer to this failure mode as vector search dilution. Even when using hybrid dense+sparse retrieval, we observed this firsthand in a deployed Wyoming Department of Transportation corpus, where scaling from 54 to 1,128 documents (88,907 chunks) reduced accuracy from 75% to below 40%. To address this dilution, we propose MASDR-RAG ( Multi-Agent Scoped Domain Retrieval for RAG) and evaluate it on 200 expert-validated queries across five LLM backbones, six corpora, and two index stacks. Our results indicate that domain scoping using organizational metadata is the key fix, significantly improving P@10 from 0.77 to 0.86 ($p < 0.05$). Furthermore, our investigation of multi-agent orchestration revealed that a high degree of configuration dependence results --creating what we call the precision-faithfulness paradox. Based on these varied outcomes, our practical recommendation is simple: scope first, then perform a single synthesis call, reserving full multi-agent orchestration for genuinely multi-domain corpora paired with native-tool-call backbones. Code and Data will be made public upon acceptance.

翻译：检索增强生成在处理大规模、异构文档集合时性能下降，此时稠密相似性失去判别能力，top-k检索越来越频繁地返回语义相似但上下文错误的内容片段。我们将这种失效模式称为向量搜索稀释。即使采用混合稠密+稀疏检索，我们在怀俄明州交通部部署的语料库中也直接观察到这一现象：当文档数量从54篇扩展到1128篇（共88,907个片段）时，准确率从75%降至40%以下。针对这一稀释问题，我们提出MASDR-RAG（基于多智能体领域限定的检索增强生成方法），并在200个经专家验证的查询上，跨5个大语言模型骨干、6个语料库和2种索引架构进行了评估。结果表明，利用组织元数据进行领域限定是关键修复手段，显著将P@10从0.77提升至0.86（p<0.05）。此外，我们对多智能体编排的探究发现，该方法存在高度配置依赖性——由此产生了我们称之为"精确-忠实悖论"的问题。基于这些差异化的实验结果，我们给出简单实用的建议：先进行领域限定，随后执行单次合成调用，仅对真正的多领域语料库保留完整的多智能体编排方案，并配合原生工具调用型骨干模型。代码和数据集将在论文接收后公开。