Saved in:
Bibliographic Details
Main Authors: Wu, Yuchuan, Zhuo, Minghan, Fu, Teng, Zhao, Mengyang, Li, Bin, Xue, Xiangyang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.07494
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915843073376256
author Wu, Yuchuan
Zhuo, Minghan
Fu, Teng
Zhao, Mengyang
Li, Bin
Xue, Xiangyang
author_facet Wu, Yuchuan
Zhuo, Minghan
Fu, Teng
Zhao, Mengyang
Li, Bin
Xue, Xiangyang
contents Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes scenarios. However, current document MLLMs still fall short of forming a complete, human-like reasoning process, because even when they improve both layout encoding and CoT-style prompting, the interaction between the two is typically learned implicitly and remains loosely coupled rather than being enforced as a systematic mechanism. So we propose DocCogito, a unified framework that integrates global layout perception with structured, region-grounded reasoning. DocCogito introduces a lightweight layout tower that distills page structure into learnable global layout prior tokens, and a deterministic Visual-Semantic Chain (VSC)-a concise structured representation less ambiguous than free-form natural-language CoT-to supervise fine-grained intermediate reasoning aligned with evidence regions. Training follows a progressive recipe, including layout perception pretraining, VSC-guided cold start, rejection sampling, and GRPO. To further strengthen the internal coupling between layout priors and VSC execution, we augment standard rewards with a fine-grained region-confidence signal that encourages reasoning traces to stay aligned with corresponding evidence regions. Extensive experiments on six benchmarks (DocVQA, WTQ, ChartQA, TextVQA, OCRBench, and InfoVQA) demonstrate strong generalization, achieving state-of-the-art results on four benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2603_07494
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding
Wu, Yuchuan
Zhuo, Minghan
Fu, Teng
Zhao, Mengyang
Li, Bin
Xue, Xiangyang
Computer Vision and Pattern Recognition
Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes scenarios. However, current document MLLMs still fall short of forming a complete, human-like reasoning process, because even when they improve both layout encoding and CoT-style prompting, the interaction between the two is typically learned implicitly and remains loosely coupled rather than being enforced as a systematic mechanism. So we propose DocCogito, a unified framework that integrates global layout perception with structured, region-grounded reasoning. DocCogito introduces a lightweight layout tower that distills page structure into learnable global layout prior tokens, and a deterministic Visual-Semantic Chain (VSC)-a concise structured representation less ambiguous than free-form natural-language CoT-to supervise fine-grained intermediate reasoning aligned with evidence regions. Training follows a progressive recipe, including layout perception pretraining, VSC-guided cold start, rejection sampling, and GRPO. To further strengthen the internal coupling between layout priors and VSC execution, we augment standard rewards with a fine-grained region-confidence signal that encourages reasoning traces to stay aligned with corresponding evidence regions. Extensive experiments on six benchmarks (DocVQA, WTQ, ChartQA, TextVQA, OCRBench, and InfoVQA) demonstrate strong generalization, achieving state-of-the-art results on four benchmarks.
title DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.07494