DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding

TL;DR

DocCogito introduces a unified framework for document understanding that combines global layout perception with structured reasoning, significantly improving evidence-grounded answers in multimodal large language models.

Contribution

The paper presents a novel integrated approach with a layout tower and Visual-Semantic Chain for explicit, evidence-grounded reasoning in document understanding tasks.

Findings

Achieves state-of-the-art results on four benchmarks

Demonstrates strong generalization across six datasets

Enhances reasoning accuracy with evidence alignment mechanisms

Abstract

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.