mlsanityData to 14 Oct 2026

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides

arXiv 2501.03936 ↗First posted 7 Jan 2025cs.AI cs.CLcited by 86

Not on the map. Why?

Cited by 27 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Automatically generating presentations from documents is a challenging task that requires accommodating content quality, visual appeal, and structural coherence. Existing methods primarily focus on improving and evaluating the content quality in isolation, overlooking visual appeal and structural coherence, which limits their practical applicability. To address these limitations, we propose PPTAgent, which comprehensively improves presentation generation through a two-stage, edit-based approach inspired by human workflows. PPTAgent first analyzes reference presentations to extract slide-level functional types and content schemas, then drafts an outline and iteratively generates editing actions based on selected reference slides to create new slides. To comprehensively evaluate the quality of generated presentations, we further introduce PPTEval, an evaluation framework that assesses presentations across three dimensions: Content, Design, and Coherence. Results demonstrate that PPTAgent significantly outperforms existing automatic presentation generation methods across all three dimensions.

Key facts. Cited by 86 papers in the map (data through 14 Oct 2026). Builds on 20 of its 41 references that are in the map. First posted on arXiv 7 Jan 2025.

Builds on

20 of 41 references.

References · 20

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  4. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  6. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  7. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 372
  8. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 334
  9. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 240
  10. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 153
  11. 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environmentcited by 107
  12. 2024A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendationscited by 85
8 more
  1. 2021DOC2PPT: Automatic Presentation Slides Generation from Scientific Documentscited by 70
  2. 2023Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofittingcited by 70
  3. 2025AutoPresent: Designing Structured Visuals from Scratchcited by 68
  4. 2021D2S: Document-to-Slide Generation Via Query-Based Text Summarizationcited by 50
  5. 2023PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completioncited by 30
  6. 2024Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approachcited by 17
  7. 2024Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attributioncited by 10
  8. 2024Knowledge-Centric Templatic Views of Documentscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 27; 2026: 59.

86 papers.

Sort:

By area:

  1. 2025Paper2Poster: Towards Multimodal Poster Automation from Scientific Paperscited by 63
  2. 2025AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarioscited by 49
  3. 2026Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoningcited by 49
  4. 2026PaperBanana: Automating Academic Illustration for AI Scientistscited by 26
  5. 2025SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Designcited by 24
  6. 2025Paper2Video: Automatic Video Generation from Scientific Paperscited by 24
  7. 2026AutoFigure: Generating and Refining Publication-Ready Scientific Illustrationscited by 23
  8. 2025Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Frameworkcited by 21
  9. 2025PresentAgent: Multimodal Agent for Presentation Video Generationcited by 21
  10. 2026DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generationcited by 18
  11. 2025PreGenie: An Agentic Framework for High-quality Visual Presentation Generationcited by 16
  12. 2025PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design Understandingcited by 14
38 more
  1. 2026PresentBench: A Fine-Grained Rubric-Based Benchmark for Slide Generationcited by 14
  2. 2025Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentationscited by 13
  3. 2025SlideTailor: Personalized Presentation Slide Generation for Scientific Paperscited by 13
  4. 2025Position: The Real Barrier to LLM Agent Usability is Agentic ROIcited by 12
  5. 2025BannerAgency: Advertising Banner Design with Multimodal LLM Agentscited by 11
  6. 2025Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulationcited by 11
  7. 2025PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMscited by 11
  8. 2025PPTArena: A Benchmark for PowerPoint Editingcited by 11
  9. 2026DECKBench: Benchmarking Multi-Agent Frameworks for Academic Slide Generation and Editingcited by 11
  10. 2026AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewardscited by 11
  11. 2026AI for Auto-Research: Roadmap & User Guidecited by 11
  12. 2026SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metricscited by 10
  13. 2026Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputscited by 9
  14. 2026AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Designcited by 9
  15. 2025PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generationcited by 8
  16. 2026SciFig: Towards Automating Editable Figure Generation for Scientific Paperscited by 8
  17. 2025Human-Agent Collaborative Paper-to-Page Craftingcited by 7
  18. 2025Paper2SysArch: Structure-Constrained System Architecture Generation from Scientific Paperscited by 7
  19. 2025Preacher: Paper-to-Video Agentic Systemcited by 6
  20. 2025LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Modelscited by 5
  21. 2025ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratchcited by 5
  22. 2025PresentCoach: Dual-Agent Presentation Coaching through Exemplars and Interactive Feedbackcited by 5
  23. 2026Any2Poster: Any-Source Poster Generation Across Modalities and Domainscited by 5
  24. 2025Textual-to-Visual Iterative Self-Verification for Slide Generationcited by 4
  25. 2026AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generationcited by 4
  26. 2026PresentAgent-2: Towards Generalist Multimodal Presentation Agentscited by 4
  27. 2026OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agentscited by 4
  28. 2025VideoAgent: Personalized Synthesis of Scientific Videoscited by 3
  29. 2026PaperX: A Unified Framework for Multimodal Academic Presentation Generation with Scholar DAGcited by 3
  30. 2026GUI-CEval: A Hierarchical and Comprehensive Chinese Benchmark for Mobile GUI Agentscited by 3
  31. 2026Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generationcited by 3
  32. 2025Addressing Situated Teaching Needs: A Multi-Agent Framework for Automated Slide Adaptationcited by 2
  33. 2026T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoningcited by 2
  34. 2026ViviDoc: Generating Interactive Documents through Human-Agent Collaborationcited by 2
  35. 2026EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolutioncited by 2
  36. 2026Demo2Tutorial: From Human Experience to Multimodal Software Tutorialscited by 2
  37. 2026ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blogcited by 2
  38. 2026Figures as Programs: Recursive Generation of Editable Scientific Figurescited by 2

50 most cited of 86 All 86 (JSON)