A Task-Centric Survey of Long-Document Visual Question Answering: Taxonomy, Evolution, and Future Directions

Yufei Tong, Guanjie Cheng, Tianle Wu, Leilei Zhang, Hang Zheng, Peihan Wu, Jianwei Yin, Shuiguang Deng · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31385 · open-access PDF

Korean

시각적 문서 이해는 시각적으로 풍부한 문서에서 지식을 습득하는 데 필수적이며 연구에 대한 관심이 커지고 있습니다.현재 설문 조사는 아키텍처 또는 기술적 접근 방식을 강조하며, 작업 뚜껑이 기술적 선택과 연구 우선 순위를 형성하는 방법에 대한 관심이 제한됩니다.우리는 긴 문서 시각적 질문 응답 (VQA)을 네 가지 구성 요소로 분해하는 작업 중심 설문 조사를 제시합니다 : 문서 분석, 증거 조직 및 검색, 생성기 조직 및 학습 및 평가.

Machine translation (Meta M2M100); the English original follows.

Abstract

Visual document understanding is essential for acquiring knowledge from visually rich documents and is attracting growing research interest. Existing surveys emphasize architectures or technical approaches, with limited attention to how task bottlenecks shape technical choices and research priorities. We present a task-centric survey that decomposes long-document visual question answering (VQA) into four components: document parsing, evidence organization and retrieval, generator organization and learning, and evaluation. For each, we develop a fine-grained taxonomy and trace motivations, tech

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31385, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange