{"ID":2830337,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.10787","arxiv_id":"2512.10787","title":"Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly","abstract":"Retrieval-Augmented Generation (RAG) systems often fail on multi-hop queries when the initial retrieval misses a bridge fact. Prior corrective approaches, such as Self-RAG, CRAG, and Adaptive-$k$, typically address this by \\textit{adding} more context or pruning existing lists. However, simply expanding the context window often leads to \\textbf{context dilution}, where distractors crowd out relevant information. We propose \\textbf{SEAL-RAG}, a training-free controller that adopts a \\textbf{``replace, don't expand''} strategy to fight context dilution under a fixed retrieval depth $k$. SEAL executes a (\\textbf{S}earch $\\rightarrow$ \\textbf{E}xtract $\\rightarrow$ \\textbf{A}ssess $\\rightarrow$ \\textbf{L}oop) cycle: it performs on-the-fly, entity-anchored extraction to build a live \\textit{gap specification} (missing entities/relations), triggers targeted micro-queries, and uses \\textit{entity-first ranking} to actively swap out distractors for gap-closing evidence. We evaluate SEAL-RAG against faithful re-implementations of Basic RAG, CRAG, Self-RAG, and Adaptive-$k$ in a shared environment on \\textbf{HotpotQA} and \\textbf{2WikiMultiHopQA}. On HotpotQA ($k=3$), SEAL improves answer correctness by \\textbf{+3--13 pp} and evidence precision by \\textbf{+12--18 pp} over Self-RAG. On 2WikiMultiHopQA ($k=5$), it outperforms Adaptive-$k$ by \\textbf{+8.0 pp} in accuracy and maintains \\textbf{96\\%} evidence precision compared to 22\\% for CRAG. These gains are statistically significant ($p\u003c0.001$). By enforcing fixed-$k$ replacement, SEAL yields a predictable cost profile while ensuring the top-$k$ slots are optimized for precision rather than mere breadth. We release our code and data at https://github.com/mosherino/SEAL-RAG.","short_abstract":"Retrieval-Augmented Generation (RAG) systems often fail on multi-hop queries when the initial retrieval misses a bridge fact. Prior corrective approaches, such as Self-RAG, CRAG, and Adaptive-$k$, typically address this by \\textit{adding} more context or pruning existing lists. However, simply expanding the context win...","url_abs":"https://arxiv.org/abs/2512.10787","url_pdf":"https://arxiv.org/pdf/2512.10787v2","authors":"[\"Moshe Lahmy\",\"Roi Yozevitch\"]","published":"2025-12-11T16:31:29Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\"]","methods":"[\"RAG\"]","has_code":false,"code_links":[{"ID":606026,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2830337,"paper_url":"https://arxiv.org/abs/2512.10787","paper_title":"Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly","repo_url":"https://github.com/mosherino/SEAL-RAG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}