Metraipolis › archive › dc_843be964014e

DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering — arXiv:2608.29037

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29037
License (as archived)
CC0-1.0
Archived
2026-10-17T07:47:27.681Z
SHA-256 of the archived text
dac9ba7d09a2198633f359a716270aa64333d054d343e3477141a246e8ee06a9
Stable URL of this page
https://metraipolis.com/documento/dc_843be964014e

How to cite

DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering — arXiv:2608.29037 — arXiv (en), https://arxiv.org/abs/2608.29037 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_843be964014e (Metraipolis archive dc_843be964014e, sha256 dac9ba7d09a2198633f359a716270aa64333d054d343e3477141a246e8ee06a9)
BibTeX
@misc{dc843be964014e,
  title = {DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering — arXiv:2608.29037},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29037},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_843be964014e; sha256 dac9ba7d09a2198633f359a716270aa64333d054d343e3477141a246e8ee06a9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29037. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-world degradations such as blur, shadow, distortion, and moire patterns severely impair the document question-answering capabilities of Multimodal Large Language Models (MLLMs). Applying restoration tools before Visual Question Answering (VQA) is an intuitive solution. However, existing restoration approaches remain limited, as manually designing and executing restoration strategies is labor-intensive and requires domain expertise. Agentic restoration offers new possibilities for automation, yet existing frameworks primarily target natural images and pursue perceptual quality, overlooking that restoration should serve downstream tasks rather than optimize generic image quality metrics. To this end, we explore the value of agentic restoration for real-world degraded document VQA and propose DocIntent, a training-free Answerability-Guided Agentic Restoration framework. DocIntent first assesses question answerability, then identifies task-relevant degradations and selectively invokes restoration tools. A Comparison-Based Rollback mechanism validates each restoration step and reverts it when question-relevant evidence becomes less decipherable. The entire process requires no additional pretrained degradation classifier or image quality assessment model. Extensive experiments on the WildDoc benchmark show that DocIntent consistently improves the average score and consistency of different open- and closed-source MLLMs. The code and experimental data will be publicly available.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.29037 — 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 2026-10-17T07:28:26.713Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).