# DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering

arXiv: https://arxiv.org/abs/2608.29037 · HTML: https://mlsanity.com/paper/2608.29037/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 21 of 21)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding](https://mlsanity.com/paper/2409.03420/) (2024)
- [TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains](https://mlsanity.com/paper/2404.19205/) (2024)
- [Harmonizing Visual Text Comprehension and Generation](https://mlsanity.com/paper/2407.16364/) (2024)
- [DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction](https://mlsanity.com/paper/2110.12942/) (2021)
- [DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks](https://mlsanity.com/paper/2405.04408/) (2024)
- [Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid](https://mlsanity.com/paper/2408.02034/) (2024)
- [UPOCR: Towards Unified Pixel-Level OCR Interface](https://mlsanity.com/paper/2312.02694/) (2023)
- [NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document Enhancement](https://mlsanity.com/paper/2404.05669/) (2024)
- [A Simple yet Effective Layout Token in Large Language Models for Document Understanding](https://mlsanity.com/paper/2503.18434/) (2025)
- [UniDemoir'e: Towards Universal Image Demoir'eing with Data Generation and Synthesis](https://mlsanity.com/paper/2502.06324/) (2025)
- [DocVXQA: Context-Aware Visual Explanations for Document Question Answering](https://mlsanity.com/paper/2505.07496/) (2025)
- [Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion](https://mlsanity.com/paper/2508.04055/) (2025)

## Abstract (arXiv)

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.