# Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations

arXiv: https://arxiv.org/abs/2510.05571 · HTML: https://mlsanity.com/paper/2510.05571/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Safety Alignment Should Be Made More Than Just a Few Tokens Deep](https://mlsanity.com/paper/2406.05946/) (2024)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation](https://mlsanity.com/paper/2412.00596/) (2024)
- [VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation](https://mlsanity.com/paper/2309.00398/) (2023)
- [AutoPresent: Designing Structured Visuals from Scratch](https://mlsanity.com/paper/2501.00912/) (2025)
- [Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers](https://mlsanity.com/paper/2505.21497/) (2025)
- [UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark](https://mlsanity.com/paper/2404.09619/) (2024)
- [MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis](https://mlsanity.com/paper/2502.18924/) (2025)
- [FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait](https://mlsanity.com/paper/2412.01064/) (2024)
- [Language-Guided Image Tokenization for Generation](https://mlsanity.com/paper/2412.05796/) (2024)
- [AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks](https://mlsanity.com/paper/2307.09724/) (2023)
- [Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation](https://mlsanity.com/paper/2505.15249/) (2025)
- [Visually-aware Recommendation with Aesthetic Features](https://mlsanity.com/paper/1905.02009/) (2019)
- [Human Aesthetic Preference-Based Large Text-to-Image Model Personalization: Kandinsky Generation as an Example](https://mlsanity.com/paper/2402.06389/) (2024)
- [Enhancing the Aesthetic Appeal of AI-Generated Physical Product Designs through LoRA Fine-Tuning with Human Feedback](https://mlsanity.com/paper/2507.02865/) (2025)

## Built on by (most cited first, 13 of 13)

- [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)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [PresentAgent-2: Towards Generalist Multimodal Presentation Agents](https://mlsanity.com/paper/2605.11363/) (2026)
- [Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety](https://mlsanity.com/paper/2601.08000/) (2026)
- [Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation](https://mlsanity.com/paper/2605.26451/) (2026)
- [Figures as Programs: Recursive Generation of Editable Scientific Figures](https://mlsanity.com/paper/2609.01006/) (2026)
- [UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings](https://mlsanity.com/paper/2605.17356/) (2026)
- [SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation](https://mlsanity.com/paper/2608.03298/) (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)
- [The Spoken Wikipedia Presentation Corpus](https://mlsanity.com/paper/2609.21676/) (2026)
- [InfoVis: Unified Slide Image Generation and Editing](https://mlsanity.com/paper/2610.16784/) (2026)

## Abstract (arXiv)

The promotion of academic papers has become an important means of enhancing research visibility. However, existing automated methods struggle limited storytelling, insufficient aesthetic quality, and constrained self-adjustment, making it difficult to achieve efficient and engaging dissemination. At the heart of those challenges is a simple principle: there is no way to improve it when you cannot evaluate it right. To address this, we introduce EvoPresent, a self-improvement agent framework that unifies coherent narratives, aesthetic-aware designs, and realistic presentation delivery via virtual characters. Central to EvoPresent is PresAesth, a multi-task reinforcement learning (RL) aesthetic model that provides reliable aesthetic scoring, defect adjustment, and comparative feedback, enabling iterative self-improvement even under limited aesthetic training data. To systematically evaluate the methods, we introduce EvoPresent Benchmark, a comprehensive benchmark comprising: textitPresentation Generation Quality, built on 650 top-tier AI conference papers with multimodal resources (slides, videos and scripts) to assess both content and design; and textitAesthetic Awareness, consisting of 2,000 slide pairs with varying aesthetic levels, supporting joint training and evaluation on scoring, defect adjustment, and comparison. Our findings highlight that (i) High-quality feedback is essential for agent self-improvement, while initial capability alone does not guarantee effective self-correction. (ii) Automated generation pipelines exhibit a trade-off between visual design and content construction. (iii) Multi-task RL training shows stronger generalization in aesthetic awareness tasks.