Paper Detail

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

arxiv Score 11.3

Published 2026-10-22 · First seen 2026-10-23

General AI

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, 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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{tong2026task,
  title = {A Task-Centric Survey of Long-Document Visual Question Answering: Taxonomy, Evolution, and Future Directions},
  author = {Yufei Tong and Guanjie Cheng and Tianle Wu and Leilei Zhang and Hang Zheng and Peihan Wu and Jianwei Yin and Shuiguang Deng},
  year = {2026},
  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 an},
  url = {https://arxiv.org/abs/2610.31385},
  keywords = {cs.CV, cs.CL, cs.IR},
  eprint = {2610.31385},
  archiveprefix = {arXiv},
}

Metadata

{}