# PreGenie: An Agentic Framework for High-quality Visual Presentation Generation

arXiv: https://arxiv.org/abs/2505.21660 · HTML: https://mlsanity.com/paper/2505.21660/

## Key facts

- Cited by 16 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 30 of its 51 references that are in the map.
- First posted on arXiv 27 May 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, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [LayoutDM: Discrete Diffusion Model for Controllable Layout Generation](https://mlsanity.com/paper/2303.08137/) (2023)
- [Referring Image Segmentation via Cross-Modal Progressive Comprehension](https://mlsanity.com/paper/2010.00514/) (2020)
- [Boosting Adversarial Training with Hypersphere Embedding](https://mlsanity.com/paper/2002.08619/) (2020)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [Semi-Supervised Learning with Normalizing Flows](https://mlsanity.com/paper/1912.13025/) (2019)
- [DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents](https://mlsanity.com/paper/2101.11796/) (2021)
- [AutoPresent: Designing Structured Visuals from Scratch](https://mlsanity.com/paper/2501.00912/) (2025)
- [MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation](https://mlsanity.com/paper/2003.12238/) (2020)
- [Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning](https://mlsanity.com/paper/2005.14310/) (2020)
- [End-to-End Optimization of Scene Layout](https://mlsanity.com/paper/2007.11744/) (2020)
- [D2S: Document-to-Slide Generation Via Query-Based Text Summarization](https://mlsanity.com/paper/2105.03664/) (2021)
- [Boosting Semantic Human Matting with Coarse Annotations](https://mlsanity.com/paper/2004.04955/) (2020)
- [PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM](https://mlsanity.com/paper/2406.02884/) (2024)
- [POSTA: A Go-to Framework for Customized Artistic Poster Generation](https://mlsanity.com/paper/2503.14908/) (2025)
- [MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio](https://mlsanity.com/paper/2503.05242/) (2025)
- [Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approach](https://mlsanity.com/paper/2406.06556/) (2024)
- [VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction](https://mlsanity.com/paper/2412.04237/) (2024)
- [Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns](https://mlsanity.com/paper/2004.09894/) (2020)
- [Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement](https://mlsanity.com/paper/2404.04627/) (2024)
- [Knowledge-Centric Templatic Views of Documents](https://mlsanity.com/paper/2401.06945/) (2024)

## Built on by (most cited first, 16 of 16)

- [DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation](https://mlsanity.com/paper/2602.22839/) (2026)
- [DECKBench: Benchmarking Multi-Agent Frameworks for Academic Slide Generation and Editing](https://mlsanity.com/paper/2602.13318/) (2026)
- [AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards](https://mlsanity.com/paper/2604.22840/) (2026)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [PresentCoach: Dual-Agent Presentation Coaching through Exemplars and Interactive Feedback](https://mlsanity.com/paper/2511.15253/) (2025)
- [Narrative-Driven Paper-to-Slide Generation via ArcDeck](https://mlsanity.com/paper/2604.11969/) (2026)
- [PresentAgent-2: Towards Generalist Multimodal Presentation Agents](https://mlsanity.com/paper/2605.11363/) (2026)
- [VideoAgent: Personalized Synthesis of Scientific Videos](https://mlsanity.com/paper/2509.11253/) (2025)
- [UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings](https://mlsanity.com/paper/2605.17356/) (2026)
- [PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs](https://mlsanity.com/paper/2608.02218/) (2026)
- [SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation](https://mlsanity.com/paper/2608.03298/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [DeepSlide: From Artifacts to Presentation Delivery](https://mlsanity.com/paper/2605.15202/) (2026)
- [Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising](https://mlsanity.com/paper/2607.00407/) (2026)
- [ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback](https://mlsanity.com/paper/2609.00226/) (2026)
- [InfoAgent: Traceable Generation and Repair of Evidence-Grounded Infographics](https://mlsanity.com/paper/2609.39380/) (2026)

## Abstract (arXiv)

Visual presentations are vital for effective communication. Early attempts to automate their creation using deep learning often faced issues such as poorly organized layouts, inaccurate text summarization, and a lack of image understanding, leading to mismatched visuals and text. These limitations restrict their application in formal contexts like business and scientific research. To address these challenges, we propose PreGenie, an agentic and modular framework powered by multimodal large language models (MLLMs) for generating high-quality visual presentations. PreGenie is built on the Slidev presentation framework, where slides are rendered from Markdown code. It operates in two stages: (1) Analysis and Initial Generation, which summarizes multimodal input and generates initial code, and (2) Review and Re-generation, which iteratively reviews intermediate code and rendered slides to produce final, high-quality presentations. Each stage leverages multiple MLLMs that collaborate and share information. Comprehensive experiments demonstrate that PreGenie excels in multimodal understanding, outperforming existing models in both aesthetics and content consistency, while aligning more closely with human design preferences.