When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval

• URL: http://arxiv.org/abs/2606.11350v1
• Date: Tue, 09 Jun 2026 18:26:24 GMT
• Title: When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval
• Abstract summary: Retrieval-augmented generation degrades when scaled to large document collections.<n>Top-k retrieval increasingly returns semantically similar but contextually incorrect chunks.<n>We propose MASDR-RAG ( Multi-Agent Scoped Domain Retrieval for RAG) to address this dilution.
• Score: 2.8753422388037486
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval [65.89247522243959]
  VisDocAgentBench is a closed-corpus benchmark comparing static and agentic retrieval under a ranked-output contract.<n>It contains 2,375 pages from 100 documents and 120 unique-target queries balanced across direct, one-bridge, and two-bridge evidence structures.<n>A strong late-interaction visual retriever reaches 97.50% Recall@1 on direct items but 2.50% on two-bridge items, exposing the limits of query--target matching when relevance depends on corpus context.
  arXiv  Detail & Related papers  (2026-08-18T15:23:06Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model [0.0]
  We run a controlled ablation study of a full agentic RAG pipeline evaluated on 5,000 questions.<n>We find that fixed hybrid retrieval via reciprocal rank fusion consistently outperforms rule-based adaptive routing.
  arXiv  Detail & Related papers  (2026-06-19T15:50:35Z)
• Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present? [3.77661940418406]
  Methods for query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval are studied.<n>We show that a strong cross-encoder reranker accounts for most of the pipeline's quality.<n>The remaining reranking and pool-expansion methods in common use, among them hierarchical summarization, graph expansion, routing, and rank fusion, give no reliable gain once that reranker is present.
  arXiv  Detail & Related papers  (2026-06-14T20:50:41Z)
• Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study [0.0]
  This paper presents a systematic empirical comparison of five retrieval strategies within a biomedical question-answering RAG pipeline.<n>All strategies share a fixed generation model (GPT-4o-mini), a common vector store (ChromaDB), and OpenAI's text-em-3-small embeddings.<n> evaluation is conducted on 250 question-answer pairs drawn from a preprocessed subset of the BioASQ benchmark.
  arXiv  Detail & Related papers  (2026-05-04T12:21:46Z)
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction [127.64173950476702]
  We study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools.<n>This approach requires no offline indexing and adapts naturally to evolving local corpora.<n>Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines.
  arXiv  Detail & Related papers  (2026-05-03T19:13:11Z)
• Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval [0.0]
  We investigate whether structured linked data, specifically.org markup and dereferenceable entity pages, can improve retrieval accuracy and answer quality in both standard and agentic RAG systems.<n>We conduct a controlled experiment across four domains (editorial, legal, travel, e-commerce) using Vertex AI Vector Search 2.0 for retrieval.
  arXiv  Detail & Related papers  (2026-03-11T12:12:51Z)
• Domain-Adaptive and Scalable Dense Retrieval for Content-Based Recommendation [0.0]
  We present a scalable dense retrieval system based on a two-tower bi-encoder, fine-tuned on the Amazon Reviews 2023 (Fashion) subset.<n>We construct training pairs from review text (as a query proxy) and item metadata (as the positive document) and fine-tune on 50,000 sampled interactions with a maximum sequence length of 500 tokens.<n>On a review-to-title benchmark over 826,402 catalog items, our approach improves Recall@10 from 0.26 (BM25) to 0.66.
  arXiv  Detail & Related papers  (2026-01-31T20:58:23Z)
• RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets [0.0]
  RAGSmith is a framework that treats RAG as an end-to-end architecture search over nine technique families and 46,080 feasible pipeline configurations.<n>We evaluate on six Wikipedia-derived domains (Law, Finance, Medicine, Defense Industry, Computer Science) each with 100 questions spanning design, interpretation, and long-answer types.<n>RAGSmith consistently outperform naive RAG configurations by +3.8% on average (range +1.2% to +6.9% across domains), with gains up to +12.5% in retrieval and +7.5% in generation.
  arXiv  Detail & Related papers  (2025-11-03T09:36:27Z)
• Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning [50.27838512822097]
  We introduce GlobalQA, the first benchmark specifically designed to evaluate global RAG capabilities.<n>We propose GlobalRAG, a multi-tool collaborative framework that preserves structural coherence through chunk-level retrieval.<n>On the Qwen2.5-14B model, GlobalRAG achieves 6.63 F1 compared to the strongest baseline's 1.51 F1.
  arXiv  Detail & Related papers  (2025-10-30T07:29:14Z)
• Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications [8.946586077722822]
  Cluster-based Adaptive Retrieval (CAR) is an algorithm that determines the optimal number of documents by analyzing the clustering patterns of ordered query-document similarity distances.<n>CAR consistently picks the optimal retrieval depth and achieves the highest TES score, outperforming every fixed top-k baseline.
  arXiv  Detail & Related papers  (2025-10-02T05:11:12Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval [92.27387459751309]
  We provide SPRINT, a unified Python toolkit for evaluating neural sparse retrieval. We establish strong and reproducible zero-shot sparse retrieval baselines across the well-acknowledged benchmark, BEIR. We show that SPLADEv2 produces sparse representations with a majority of tokens outside of the original query and document.
  arXiv  Detail & Related papers  (2023-07-19T22:48:02Z)
• UnifieR: A Unified Retriever for Large-Scale Retrieval [84.61239936314597]
  Large-scale retrieval is to recall relevant documents from a huge collection given a query. Recent retrieval methods based on pre-trained language models (PLM) can be coarsely categorized into either dense-vector or lexicon-based paradigms. We propose a new learning framework, UnifieR which unifies dense-vector and lexicon-based retrieval in one model with a dual-representing capability.
  arXiv  Detail & Related papers  (2022-05-23T11:01:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.