Metraipolis › archive › dc_08ab0902ca41

Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement — arXiv:2608.16628

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.16628
License (as archived): CC0-1.0
Archived: 2026-10-18T17:45:11.720Z
SHA-256 of the archived text: f0c4fae06af81357ed491b07c437a4791bed89e1daa3ca711a492a99c54184d6
Stable URL of this page: https://metraipolis.com/documento/dc_08ab0902ca41

How to cite

Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement — arXiv:2608.16628 — arXiv (en), https://arxiv.org/abs/2608.16628 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08ab0902ca41 (Metraipolis archive dc_08ab0902ca41, sha256 f0c4fae06af81357ed491b07c437a4791bed89e1daa3ca711a492a99c54184d6)

BibTeX

@misc{dc08ab0902ca41,
  title = {Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement — arXiv:2608.16628},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16628},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08ab0902ca41; sha256 f0c4fae06af81357ed491b07c437a4791bed89e1daa3ca711a492a99c54184d6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16628. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern Multimodal Retrieval-Augmented Generation (M-RAG) systems are fundamentally limited by the binary connectivity paradigm of traditional simple graphs, which fails to capture the intricate, high-order correlations among heterogeneous entities, such as the N-ary relationships between a visual chart, its scattered textual descriptions, and underlying numerical data. Furthermore, existing refinement strategies often rely on exhaustive, full-page reconstruction to align cross-modal information, leading to prohibitive computational redundancy and the introduction of contextual noise in long-form document processing. In this paper, we propose Hyper-M2RAG, a novel framework that redefines multimodal document retrieval through High-order Hypergraph Representation Learning. We first formalize the document structure as a Multimodal Hypergraph, utilizing hyperedges as unified semantic containers to encapsulate multi-way associations across text, images, and tables, thereby transcending point-to-point modeling. To mitigate semantic fragmentation caused by physical pagination, we introduce an Anchor-driven Incremental Refinement mechanism. Rather than performing a global sweep, our approach identifies boundary-crossing anchor nodes and reconstructs their local hyper-topology using one-hop neighborhood contexts. This targeted refinement effectively bridges cross-page knowledge gaps with minimal computational footprints. Extensive evaluations on multimodal benchmarking datasets demonstrate that Hyper-M2RAG significantly outperforms state-of-the-art methods in both retrieval precision and generation coherence. Our code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16628 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.884Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).