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

2026-04-21

AI Summary

This work addresses the poor layout quality of slides generated by large language models, which stems from their text-centric nature and neglect of visual aesthetics. To remedy this, the authors propose a reinforcement learning framework guided by verifiable rewards that explicitly incorporate quantifiable aesthetic principles—such as white space utilization, element collision avoidance, and visual balance—as supervisory signals. Leveraging the GRPO algorithm, the model is efficiently fine-tuned on GLM-4.7-Flash using only 5K samples. Experimental results demonstrate substantial improvements: layout compliance increases from 36% to 85%, while issues related to insufficient white space, element collisions, and visual imbalance are reduced by 44%, 43%, and 28%, respectively. Human evaluators also rate the generated layouts 7.6% higher, significantly outperforming existing approaches.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• slide generation
• aesthetic layout
• modality gap
• visual aesthetics
• LLM-based generation

Innovation

• verifiable rewards
• aesthetic layout
• slide generation
• reinforcement learning
• LLM-based design