{"ID":23475900,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19417","arxiv_id":"2609.19417","title":"Less Is More: Graph-free Multimodal RAG via Multi-signal Late Fusion","abstract":"Graph-based retrieval-augmented generation (RAG) is widely used for multimodal, cross-document question answering. However, building corpus-level graphs is expensive, slow to query, and difficult to maintain. We present TrioRAG, a graph-free multimodal framework that integrates evidence from three complementary signals: the question, the anchor image, and a VLM-enhanced query generated from both. Each signal retrieves independently over a shared multi-vector index of page text and page images, and the results are combined through late fusion. Further, we introduce AutoQA, a multimodal automotive benchmark whose questions are grounded in noisy, web-sourced images rather than clean document-sourced figures. Its questions require reasoning across manuals. We position it as a model-curated testbed rather than a human-validated gold standard. Across three benchmarks, TrioRAG matches or outperforms graph-based systems while reducing total cost and accelerating per-query inference by 1.6-2.3 times. By construction, AutoQA grounds its questions in out-of-corpus web images. In this setting image retrieval reaches only 19.3% document-level recall, while text-derived signals, especially the VLM-enhanced query, keep retrieval robust.","short_abstract":"Graph-based retrieval-augmented generation (RAG) is widely used for multimodal, cross-document question answering. However, building corpus-level graphs is expensive, slow to query, and difficult to maintain. We present TrioRAG, a graph-free multimodal framework that integrates evidence from three complementary signals...","url_abs":"https://arxiv.org/abs/2609.19417","url_pdf":"https://arxiv.org/pdf/2609.19417v1","authors":"[\"Tithi Rakshit\",\"Hongkuan Zhou\",\"Lavdim Halilaj\",\"Yuqicheng Zhu\"]","published":"2026-09-16T20:54:08Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"RAG\"]","has_code":false}