Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation

Zhiyao Cui; Chenxu Wang; Shuyue Hu; Yiqun Zhang; Wenqi Shao; Qiaosheng Zhang; Zhen Wang

cs.HCApr 8, 2026

Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation

Authors: Zhiyao Cui, Chenxu Wang, Shuyue Hu, Yiqun Zhang, Wenqi Shao, Qiaosheng Zhang, Zhen Wang

Organizations: School of Cybersecurity, Northwestern Polytechnical University · Shanghai Artificial Intelligence Laboratory · Shanghai Innovation Institution · Fudan University

Abstract

Producing presentation slides automatically entails coordinating narrative structure with page-level graphic design under strict spatial constraints. For such structured multimodal tasks, a well-organized design process is essential to ensure the final quality of slides. Existing approaches rely on fixed templates or directly emit executable code, thereby both limiting the creative layout-design capabilities of LLMs and bypassing the essential slide-page design step. To address these limitations, this paper (1) proposes a hierarchical slides generation workflow, DeepSlides, that systematically organizes slide design tasks without any predefined template or style, decoupling slide-page design from implementation; (2) introduces SlideDesign, a dataset tailored specifically for slides generation tasks; and (3) presents a multi-agent reinforcement learning training paradigm and trains a couple of models, SlideQwens, for slide design and implementation. Experimental results demonstrate that our proposed framework outperforms baseline methods on evaluated metrics and achieves superior performance in human preference evaluations. The dataset and code are available at https://github.com/sxswz213/DeepSlides.

Figures & tables

Figure 1: Overview of the DeepSlides workflow. Given a topic and optional user-specified page-level requirements, the system first determines the high-level slide style. Subsequently, each slide is generated through iterative refinement.

Figure 2: Comparative visualization of slide decks generated for the topic "Urban Heat Island Mitigation", contrasting slides produced by direct model generation, Auto-Slides, EvoPresent, DeepSlides (ours), and two commercial solutions, Manus and Kimi. Additional cases can be found in Appendix F .

	Output Format	Complete Presentation	Template Free
EvoPresent	HTML	✓	$\times$
AutoSlides	LaTeX/PDF	✓	$\times$
SlideGen	PPTX	✓	$\times$
SlideCoder	PPTX	$\times$	$\times$
DOC2PPT	PPTX/PDF	✓	$\times$
PPTAgent	PPTX/HTML	✓	$\times$

Table 1: Comparison of slide-generation workflows. light blue rows indicate open-source methods, while light orange rows denote closed-source systems.

Figure 3: Illustration of the DeepSlides hierarchical slides generation workflow. The framework begins by generating a detailed outline through multimodal deep research or directly from user-provided outlines. Subsequently, slide-level style guidelines are defined, including colors, shapes, and backgrounds. At the page-level, the system performs content expansion via web search and executes detailed design across background, layout, and content layers. Python code is generated to implement each slide, followed by iterative refinement based on evaluation and feedback. Finally, completed slides are assembled into a cohesive presentation.

Figure 4: Examples of data in SlideDesign.

Figure 6: Subject taxonomy and dataset composition. Inner ring: 6 primary areas with counts; outer ring: 42 secondary disciplines.

Method	Objective Metrics		Content		Visual
Method	Success Rate (%)	Balance ( $\uparrow$ )	Clarity	Coherence	Layout	Hierarchy	Color	Avg.
Direct ${}_{Claude~Haiku}$	99	0.53	3.99	3.64	2.64	3.87	3.14	3.46
Direct ${}_{Claude~Sonnet}$	97	0.67	3.79	3.47	2.67	3.64	3.13	3.34
Auto-Slides ${}_{Claude~Haiku}$	87	0.81	3.53	3.64	2.49	3.50	3.08	3.25
EvoPresent ${}_{Claude~Haiku}$	100	0.77	3.53	3.84	3.46	3.95	3.69	3.69
DeepSlides ${}_{Claude~Haiku}$	95	0.78	3.79	3.81	3.55	4.04	3.71	3.78

Table 2: We compare baseline systems and DeepSlides variants using objective metrics and VLM-as-judge scores for content quality and visual design. Best and second-best results are highlighted in bold and underline , respectively.

Figure 8: We report the fraction of topics for which each framework is ranked #1 by human evaluators.

Figure 9: Pairwise win rate.

Figure 10: Human evaluation scores.

Model	Success Rate	Balance	Visual
Qwen3-0.6B	0.0	-	-
SlideQwens sft	81.4	0.77	3.23
SlideQwens full	86.0	0.77	3.38

Table 3: Model Training Performance Comparison.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 11: Detailed information on the human evaluation questionnaire.

Figure 12: Detailed information on the human evaluation questionnaire.

LLM Agent Workflow Optimization

LLM agent workflow optimization studies how to design and run multi-step agents for better task success, reliability, latency, and cost.

See all 260 papers

AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards
Apr 21, 2026Yiming Pan, Chengwei Hu, Xuancheng Huang +6LLM Alignment Reinforcement Learning with Verifiable Rewards
Beijing Institute of Technology · Zhipu AI (Z.ai)
DeepSlide: From Artifacts to Presentation Delivery
Apr 1, 2026Ming Yang, Zhiwei Zhang, Jiahang Li +3Human-in-the-Loop AI
School of Data Science, Fudan University, Shanghai, China
Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising
Jul 1, 2026Tianci Liu, Zihan Dong, Linjun Zhang +5
Purdue University · Microsoft · Rutgers University +1

Apr 21, 2026J/K move · Enter open · S save

AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards

Yiming Pan, Chengwei Hu, Xuancheng Huang, Can Huang+5

Beijing Institute of Technology · Zhipu AI (Z.ai)

LLM Alignment Reinforcement Learning with Verifiable Rewards RL for Generative Models

Open paper AskPDF arXiv

Large language models (LLMs) have demonstrated strong potential in agentic tasks, particularly in slide generation. However, slide generation poses a fundamental challenge: the generation process is text-centric, whereas its quality is governed by visual aesthetics. This modality gap leads current models to frequently produce slides with aesthetically suboptimal layouts. Existing solutions typically rely either on heavy visual reflection, which incurs high inference cost yet yields limited gains; or on fine-tuning with large-scale datasets, which still provides weak and indirect aesthetic supervision. In contrast, the explicit use of aesthetic principles as supervision remains unexplored. In this work, we present AeSlides, a reinforcement learning framework with verifiable rewards for Aesthetic layout supervision in Slide generation. We introduce a suite of meticulously designed verifiable metrics to quantify slide layout quality, capturing key layout issues in an accurate, efficient, and low-cost manner. Leveraging these verifiable metrics, we develop a GRPO-based reinforcement learning method that directly optimizes slide generation models for aesthetically coherent layouts. With only 5K training prompts on GLM-4.7-Flash, AeSlides improves aspect ratio compliance from 36% to 85%, while reducing whitespace by 44%, element collisions by 43%, and visual imbalance by 28%. Human evaluation further shows a substantial improvement in overall quality, increasing scores from 3.31 to 3.56 (+7.6%), outperforming both model-based reward optimization and reflection-based agentic approaches, and even edging out Claude-Sonnet-4.5. These results demonstrate that such a verifiable aesthetic paradigm provides an efficient and scalable approach to aligning slide generation with human aesthetic preferences. Our repository is available at https://github.com/ympan0508/aeslides.

Abstract

LLM Agent Workflow Optimization

Explore similar work

AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards

DeepSlide: From Artifacts to Presentation Delivery

Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising