mlsanityData to 14 Oct 2026

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

arXiv 2510.26615 ↗First posted 30 Oct 2025cs.CLcited by 3

On the map: LLM agents and tool use → Multimodal and embodied agents

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%).

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.

Builds on

29 of 71 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding18 Mar

Other references · 28

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  3. 2019Towards VQA Models That Can Readcited by 1,718
  4. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  5. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  6. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  7. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  8. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 615
  9. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 553
  10. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 408
  11. 2019FUNSD: A Dataset for Form Understanding in Noisy Scanned Documentscited by 349
  12. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documentscited by 245
16 more
  1. 2023SlideVQA: A Dataset for Document Visual Question Answering on Multiple Imagescited by 179
  2. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 153
  3. 2021VisualMRC: Machine Reading Comprehension on Document Imagescited by 151
  4. 2021Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformercited by 134
  5. 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Tokencited by 125
  6. 2023DocLLM: A layout-aware generative language model for multimodal document understandingcited by 116
  7. 2024M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understandingcited by 111
  8. 2021DOC2PPT: Automatic Presentation Slides Generation from Scientific Documentscited by 70
  9. 2025ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agentscited by 66
  10. 2019BERTgrid: Contextualized Embedding for 2D Document Representation and Understandingcited by 63
  11. 2025VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documentscited by 59
  12. 2021D2S: Document-to-Slide Generation Via Query-Based Text Summarizationcited by 50
  13. 2021Document Collection Visual Question Answeringcited by 45
  14. 2024MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMscited by 39
  15. 2025REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmarkcited by 35
  16. 2024AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrationscited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Exploring Information Seeking Agent Consolidationcited by 0
  2. 2026BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprintscited by 0
  3. 2026It Takes Workflows to Evolve Better Workflowscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling
  2. 2025Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding
  3. 2025SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations
  4. 2026SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts
  5. 2026VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents
  6. 2025DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding
  7. 2025PathAgent: Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning
  8. 2025ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering