SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation

• URL: http://arxiv.org/abs/2608.03298v1
• Date: Tue, 04 Aug 2026 08:08:28 GMT
• Title: SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation
• Abstract summary: We present SeaSlides, an agentic slide-generation framework built around a semantic abstraction layer.<n>Rather than authoring coordinates, inline styles, or SVG raw geometry, the model writes structured slide content through reusable components and capability modules.<n>For evaluation, we combine the 128-task UltraPresent validation setting with SeaSlidesBench-Rich, a new 32-task benchmark stressing mathematics, code, pseudocode, tables, charts, and diagrams.
• Score: 23.344472571293917
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic presentation generation must preserve source content, maintain coherent visual design, render specialized objects, and produce usable artifacts. Existing systems meet only part of this requirement: templates preserve regularity but restrict adaptation, whereas free-form HTML or SVG gives models flexibility at the cost of low-level rendering decisions. This mismatch makes long technical decks brittle, especially when slides contain formulas, code, or data graphics. We present SeaSlides, an agentic slide-generation framework built around a semantic abstraction layer. Rather than authoring coordinates, inline styles, or raw SVG geometry, the model writes structured slide content through reusable components and capability modules, while templates own layout, style, and rendering. We instantiate this principle separately in HTML and Typst: SeaSlides-HTML uses template-defined DOM components, whereas SeaSlides-Typst uses template functions and package-backed modules. Capability modules route equations, code, and charts to dedicated renderers, and three feedback stages localize build errors, project-constraint violations, and visual defects before export. The two systems retain backend-specific syntax and contracts while sharing the same authoring boundary. For evaluation, we combine the 128-task UltraPresent validation setting with SeaSlidesBench-Rich, a new 32-task benchmark stressing mathematics, code, pseudocode, tables, charts, and diagrams. Across four generation models, both SeaSlides backends produce more readable, content-oriented source than SVG-heavy generation. A SeaSlides backend attains the highest rich-content macro-average under three of the four models while maintaining competitive overall qualitative performance. These results support semantic abstraction as a practical authoring principle across presentation backends.

Related papers

• A Dual-Track Framework for Template-Constrained LaTeX Conversion [1.906311743485569]
  Existing approaches largely depend on either deterministic rule-based converters or pure end-to-end Large Language Model (LLM) generation.<n>We introduce a robust Dual-Track Framework that systematically decouples template formatting from document processing.<n>Our method achieves better structural fidelity, diverse layout, and achieves a higher compilation success rate compared to the previous baselines.
  arXiv  Detail & Related papers  (2026-06-22T09:51:11Z)
• Imagine Before You Draw: Visual Prompt Engineering for Image Generation [67.81347924426714]
  We propose Visual Prompt Engineering (VPE), which can be seamlessly integrated into internal frameworks.<n>We validate VPE across class-conditional generation, text-to-image generation, and image editing.<n>Results show that VPE can accelerate convergence, raise quality ceilings, and through internal integration, achieve substantially better editing preservation.
  arXiv  Detail & Related papers  (2026-06-03T05:01:36Z)
• Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions [22.596430902964272]
  Existing automation methods mostly follow fixed template filling and cannot support dynamic updates for diverse, user-authored slide decks.<n>We introduce DynaSlide, a large-scale benchmark with 20,036 real-world instruction-execution triples (source slide, user instruction, target slide) grounded in a shared external database.<n>We propose SlideAgent, an agent-based framework that combines multimodal slide parsing, natural language instruction grounding, and tool-augmented reasoning for tables, charts, and textual conclusions.
  arXiv  Detail & Related papers  (2026-04-20T07:11:24Z)
• Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation [37.32710542829869]
  This paper proposes a hierarchical slides generation workflow, DeepSlides, that organizes slide design tasks without any predefined template or style.<n> Experimental results demonstrate that our proposed framework outperforms baseline methods on evaluated metrics and achieves superior performance in human preference evaluations.
  arXiv  Detail & Related papers  (2026-04-08T06:50:37Z)
• Multimodal OCR: Parse Anything from Documents [72.69545534962234]
  dots.mocr treats visual elements such as charts, diagrams, tables, and icons as first-class parsing targets.<n>It reconstructs both text and graphics as structured outputs, enabling more faithful document reconstruction.<n>It supports end-to-end training over heterogeneous document elements.
  arXiv  Detail & Related papers  (2026-03-13T14:42:21Z)
• DynaPURLS: Dynamic Refinement of Part-aware Representations for Skeleton-based Zero-Shot Action Recognition [51.80782323686666]
  We introduce textbfDynaPURLS, a unified framework that establishes robust, multi-scale visual-semantic correspondences.<n>Our framework leverages a large language model to generate hierarchical textual descriptions that encompass both global movements and local body-part dynamics.<n>Experiments on three large-scale benchmark datasets, including NTU RGB+D 60/120 and PKU-MMD, demonstrate that DynaPURLS significantly outperforms prior art.
  arXiv  Detail & Related papers  (2025-12-12T10:39:10Z)
• AICC: Parse HTML Finer, Make Models Better -- A 7.3T AI-Ready Corpus Built by a Model-Based HTML Parser [54.623900859999424]
  We introduce MinerU-HTML, a novel extraction pipeline that reformulates content extraction as a sequence labeling problem.<n>On MainWebBench, our benchmark of 7,887 annotated web pages, MinerU-HTML 81.8% ROUGE-N F1 compared to Trafilatura's 63.6%, with exceptional structured element preservation.
  arXiv  Detail & Related papers  (2025-11-20T14:15:23Z)
• Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling [32.22298939812003]
  We introduce SliDer, a novel framework that uses Vision-Language Models to derender slide images as compact and editable SVG representations.<n>SliDer achieves a reconstruction LPIPS of 0.069 and is favored by human evaluators in 82.9% of cases compared to the strongest zero-shot VLM baseline.
  arXiv  Detail & Related papers  (2025-11-17T15:16:13Z)
• LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models [84.16541551923221]
  We propose a model that treats layout generation as a code generation task to enhance semantic information. We develop a Code Instruct Tuning (CIT) approach comprising three interconnected modules. We attain significant state-of-the-art performance on multiple datasets.
  arXiv  Detail & Related papers  (2023-09-18T06:35:10Z)
• ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpages [66.45377533562417]
  We propose a solution for "zero-shot" open-domain relation extraction from webpages with a previously unseen template. Our model uses a graph neural network-based approach to build a rich representation of text fields on a webpage.
  arXiv  Detail & Related papers  (2020-05-14T16:15:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.