# SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding

arXiv: https://arxiv.org/abs/2510.26615 · HTML: https://mlsanity.com/paper/2510.26615/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 71 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 29 of 29)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [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)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [VisualMRC: Machine Reading Comprehension on Document Images](https://mlsanity.com/paper/2101.11272/) (2021)
- [Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer](https://mlsanity.com/paper/2102.09550/) (2021)
- [xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token](https://mlsanity.com/paper/2405.13792/) (2024)
- [DocLLM: A layout-aware generative language model for multimodal document understanding](https://mlsanity.com/paper/2401.00908/) (2023)
- [M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding](https://mlsanity.com/paper/2411.04952/) (2024)
- [DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents](https://mlsanity.com/paper/2101.11796/) (2021)
- [MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding](https://mlsanity.com/paper/2503.13964/) (2025)
- [ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents](https://mlsanity.com/paper/2502.18017/) (2025)
- [BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding](https://mlsanity.com/paper/1909.04948/) (2019)
- [VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents](https://mlsanity.com/paper/2504.09795/) (2025)
- [D2S: Document-to-Slide Generation Via Query-Based Text Summarization](https://mlsanity.com/paper/2105.03664/) (2021)
- [Document Collection Visual Question Answering](https://mlsanity.com/paper/2104.14336/) (2021)
- [MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs](https://mlsanity.com/paper/2410.12332/) (2024)
- [REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark](https://mlsanity.com/paper/2502.12342/) (2025)
- [AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations](https://mlsanity.com/paper/2411.13451/) (2024)

## Built on by (most cited first, 3 of 3)

- [Exploring Information Seeking Agent Consolidation](https://mlsanity.com/paper/2602.00585/) (2026)
- [BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints](https://mlsanity.com/paper/2609.07362/) (2026)
- [It Takes Workflows to Evolve Better Workflows](https://mlsanity.com/paper/2610.01026/) (2026)

## Abstract (arXiv)

Multi-page visual documents such as manuals, brochures, presentations, and posters convey key information through layout, colors, icons, and cross-slide references. While multimodal large language models (MLLMs) offer opportunities in document understanding, current systems struggle with complex, multi-page visual documents, particularly in fine-grained reasoning over elements and pages. We introduce SlideAgent, a versatile agentic framework for understanding multi-modal, multi-page, and multi-layout documents, especially slide decks. SlideAgent employs specialized agents and decomposes reasoning into three specialized levels--global, page, and element--to construct a structured, query-agnostic representation that captures both overarching themes and detailed visual or textual cues. During inference, SlideAgent selectively activates specialized agents for multi-level reasoning and integrates their outputs into coherent, context-aware answers. Extensive experiments show that SlideAgent significantly improves accuracy over both proprietary (+7.9%) and open-source models (+9.8%).