# SlideGen: Collaborative Multimodal Agents for Scientific Slide Generation

arXiv: https://arxiv.org/abs/2512.04529 · HTML: https://mlsanity.com/paper/2512.04529/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2025.

## Built on by (most cited first, 25 of 25)

- [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)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [SciFig: Towards Automating Editable Figure Generation for Scientific Papers](https://mlsanity.com/paper/2601.04390/) (2026)
- [Quantifying Trust: Financial Risk Management for Trustworthy AI Agents](https://mlsanity.com/paper/2604.03976/) (2026)
- [Narrative-Driven Paper-to-Slide Generation via ArcDeck](https://mlsanity.com/paper/2604.11969/) (2026)
- [When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning](https://mlsanity.com/paper/2605.03314/) (2026)
- [PresentAgent-2: Towards Generalist Multimodal Presentation Agents](https://mlsanity.com/paper/2605.11363/) (2026)
- [The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination](https://mlsanity.com/paper/2601.08237/) (2026)
- [PaperX: A Unified Framework for Multimodal Academic Presentation Generation with Scholar DAG](https://mlsanity.com/paper/2602.03866/) (2026)
- [Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation](https://mlsanity.com/paper/2605.26451/) (2026)
- [ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://mlsanity.com/paper/2603.27991/) (2026)
- [ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog](https://mlsanity.com/paper/2607.04438/) (2026)
- [UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings](https://mlsanity.com/paper/2605.17356/) (2026)
- [MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision](https://mlsanity.com/paper/2606.17162/) (2026)
- [SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation](https://mlsanity.com/paper/2608.03298/) (2026)
- [Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models](https://mlsanity.com/paper/2512.20954/) (2025)
- [Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://mlsanity.com/paper/2603.01912/) (2026)
- [Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising](https://mlsanity.com/paper/2607.00407/) (2026)
- [When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models](https://mlsanity.com/paper/2608.30395/) (2026)
- [ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation](https://mlsanity.com/paper/2609.00194/) (2026)
- [ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback](https://mlsanity.com/paper/2609.00226/) (2026)
- [SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts](https://mlsanity.com/paper/2609.03109/) (2026)
- [SLATE: Are AI-Generated Slides Educationally Effective? A Benchmark for Language Teaching Quality and Learner Knowledge Acquisition](https://mlsanity.com/paper/2609.06212/) (2026)
- [SlideLab: Audience-Centered Scientific Slide Generation and Evaluation](https://mlsanity.com/paper/2609.30294/) (2026)

## Abstract (arXiv)

Creating presentation slides from scientific papers is not simply a matter of summarizing paragraphs. A presenter is required to decide what story to tell, which figures and equations to highlight, and how to arrange them into pages that are visually clear rather than crowded or repetitive. The need to jointly reason over long contexts and layout-sensitive design makes paper-to-slide generation a uniquely challenging multimodal task. Most existing approaches, however, focus mainly on textual content selection, producing slides that often lack visual balance, narrative flow, or coherent integration of multimodal evidence. In this work, we introduce SlideGen, a collaborative vision-language multi-agent framework that coordinates narrative planning, multimodal grounding, and layout composition. SlideGen assigns specialized agents to outline the presentation structure, align supporting figures and tables with key claims, generate speaker notes, and compose editable PPTX slides through a diverse layout library. By refining layouts at the deck level, the system produces slide decks that are both faithful to the source paper and effective as presentations. To evaluate slide generation beyond text fidelity, we propose geometry-aware density (GAD), a metric that captures visual clutter, sparsity, and fragmentation, and shows strong agreement with human judgments. Evaluated across four complementary dimensions on our 200-paper benchmark, SlideGen consistently and significantly improves layout balance, content coverage, and text coherence, outperforming competitive baselines in paper-to-slide generation. Our findings suggest that effective slide generation requires multimodal design reasoning, and that agent collaboration offers a principled bridge between document understanding and scientific communication.