Yufei Tong, Guanjie Cheng, Tianle Wu, Leilei Zhang, Hang Zheng, Peihan Wu, Jianwei Yin, Shuiguang Deng · 2026 · Preprints.org
DOI: 10.20944/preprints202610.2118.v1 · cited by 0 works (OpenAlex) · open-access PDF
La comprensión de documentos visuales es esencial para adquirir conocimientos de documentos visualmente ricos y está atrayendo un interés cada vez mayor en la investigación. Las encuestas existentes enfatizan arquitecturas o enfoques técnicos, con una atención limitada a cómo las barreras de tareas forman opciones técnicas y prioridades de investigación. Presentamos una encuesta centrada en tareas que descompone la respuesta visual a preguntas de documentos largos (VQA) en cuatro componentes: análisis de documentos, organización y recuperación de evidencias, organización y aprendizaje de generadores y evaluación. Para cada uno, desarrollamos una taxonomía de grano fino y motivaciones de rastreo, respuestas técnicas y conexiones intercomponentes. Nosotros nos enfocamos en la recuperación explícita mientras cubrimos la lectura directa. Nuestro análisis temporal rastrea prioridades que van desde la comprensión multimodal
Machine translation (Meta M2M100); the English original follows.
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, technical responses, and cross-component connections. We focus on explicit retrieval while covering direct reading. Our temporal analysis traces expanding priorities from multimodal content understanding to sufficient, high-fidelity evidence acquisition and sustained evidence management. We outline future directions in evidence sufficiency, verifiable and correctable understanding, and budget-aware coordination, with an outlook on continual document understanding.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Task (project management), TRACE (psycholinguistics), Focus (optics), Verifiable secret sharing, Question answering
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange