{"ID":5937875,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T03:01:22.582788088Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04625","arxiv_id":"2607.04625","title":"Hierarchical Evidence-Driven Reasoning for Long Document Understanding","abstract":"Retrieval-Augmented Generation (RAG) streamlines long-document understanding by leveraging retrieval mechanisms to restrict input images to a highly curated subset. However, existing multimodal RAG pipelines primarily face two critical challenges: first, standard semantic similarity retrievers frequently fetch topically overlapping yet answer-void distractor pages that mislead downstream generation; second, rigid single-pass pipelines heavily depend on initial retrieval success, where any omission of core evidence inevitably causes cascading errors. To address these challenges, we introduce HIEVI-RAG, a hierarchical, evidence-driven multimodal RAG framework for closed-domain document understanding. HIEVI-RAG systematically factorizes complex queries into a cooperative four-stage pipeline: (1) hierarchical question decomposition to break multi-hop root queries into atomic child questions; (2) coarse visual page retrieval leveraging a multimodal retriever to fetch candidate pages based on semantic similarity; (3) fine-grained page verification via EVIAGENT, a specialized multi-page verifier trained with GRPO to execute cross-page reasoning over multi-image blocks; and (4) memory-guided iterative generation that leverages accumulated sub-question context to execute multi-round, dynamic reasoning over the prioritized sequence. Extensive evaluations across four benchmarks demonstrate the robust efficacy and synergy of our framework, which significantly outperforms existing open-source baselines and exceeds the strongest reported baseline by an average of 8.05% in accuracy.","short_abstract":"Retrieval-Augmented Generation (RAG) streamlines long-document understanding by leveraging retrieval mechanisms to restrict input images to a highly curated subset. However, existing multimodal RAG pipelines primarily face two critical challenges: first, standard semantic similarity retrievers frequently fetch topicall...","url_abs":"https://arxiv.org/abs/2607.04625","url_pdf":"https://arxiv.org/pdf/2607.04625v1","authors":"[\"Junyu Xiong\",\"Yonghui Wang\",\"Rongjian Gu\",\"Chenyu Liu\",\"Bing Yin\",\"Wengang Zhou\",\"Houqiang Li\"]","published":"2026-07-06T03:08:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"RAG\"]","has_code":false}