Metraipolis › archive › dc_59acfb58dbc8

An Empirical Study of VLM Pipelines for Long-Document QA — arXiv:2609.29933

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29933
License (as archived)
CC0-1.0
Archived
2026-10-08T04:27:52.176Z
SHA-256 of the archived text
545e37d27bdbd012a6d84188eb0cc42193279af25844681e322a228fd7fff44b
Stable URL of this page
https://metraipolis.com/documento/dc_59acfb58dbc8

How to cite

An Empirical Study of VLM Pipelines for Long-Document QA — arXiv:2609.29933 — arXiv (en), https://arxiv.org/abs/2609.29933 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_59acfb58dbc8 (Metraipolis archive dc_59acfb58dbc8, sha256 545e37d27bdbd012a6d84188eb0cc42193279af25844681e322a228fd7fff44b)
BibTeX
@misc{dc59acfb58dbc8,
  title = {An Empirical Study of VLM Pipelines for Long-Document QA — arXiv:2609.29933},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29933},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_59acfb58dbc8; sha256 545e37d27bdbd012a6d84188eb0cc42193279af25844681e322a228fd7fff44b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29933. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language Models (VLMs) are increasingly used for long-document processing, where the inputs combine text with charts, tables, figures, and complex layouts. Deploying them means choosing how to feed the document to the model, which retriever to use when only a subset of pages is sent, and whether to run the model agentically or as a static pipeline. We study these choices on two long-document QA benchmarks with both frontier API and open-weight VLMs. First, on MMLongBench-Doc our six-tool agent with page, table, figure, and search calls pays off only once the answering VLM is large enough: with Qwen3.5-4B and 9B it trails static page input, with Qwen3.5-27B it draws level, and with Sonnet 4.5 it leads. On LongDocURL it is level with or ahead of static input at every reader. Its lead over the strongest static pipeline is clearest with the frontier reader on MMLongBench-Doc and narrows to within noise on LongDocURL. Second, retrieval modality matters more than the specific retriever: the strongest image retriever leads the strongest text pipeline, and on the text side a single off-the-shelf cross-encoder rerank essentially matches a much heavier multi-stage LLM pipeline. Top-k image retrieval is also the most token-efficient input at every reader we paired it with, at roughly a seventh to a quarter of the tokens of sending every page. Third, cutting across all three choices, three of our strongest pipelines succeed on different questions, and an oracle that picks the best pipeline per question gains roughly thirteen points over the best single pipeline, though evidence-type routing recovers almost none of it.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.29933 — 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 2026-10-08T03:50:58.186Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).