Pith. sign in

REVIEW 6 cited by

PreGenie: An Agentic Framework for High-quality Visual Presentation Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.21660 v2 pith:5EPDMA4Q submitted 2025-05-27 cs.LG

PreGenie: An Agentic Framework for High-quality Visual Presentation Generation

classification cs.LG
keywords pregeniecodeframeworkhigh-qualitymultimodalpresentationsvisualagentic
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Visual presentations are vital for effective communication. Early attempts to automate their creation using deep learning often faced issues such as poorly organized layouts, inaccurate text summarization, and a lack of image understanding, leading to mismatched visuals and text. These limitations restrict their application in formal contexts like business and scientific research. To address these challenges, we propose PreGenie, an agentic and modular framework powered by multimodal large language models (MLLMs) for generating high-quality visual presentations. PreGenie is built on the Slidev presentation framework, where slides are rendered from Markdown code. It operates in two stages: (1) Analysis and Initial Generation, which summarizes multimodal input and generates initial code, and (2) Review and Re-generation, which iteratively reviews intermediate code and rendered slides to produce final, high-quality presentations. Each stage leverages multiple MLLMs that collaborate and share information. Comprehensive experiments demonstrate that PreGenie excels in multimodal understanding, outperforming existing models in both aesthetics and content consistency, while aligning more closely with human design preferences.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. OmniPresent: Generating Coherent Presentation Suites from Scientific Papers

    cs.SE 2026-07 conditional novelty 6.5

    A multi-agent HTML pipeline with shared knowledge and cross-artifact verify-and-repair generates coherent poster/slides/video/page suites from papers and beats specialized baselines on OmniPreBench.

  2. PresentAgent-2: Towards Generalist Multimodal Presentation Agents

    cs.CV 2026-05 unverdicted novelty 6.0

    PresentAgent-2 generates query-driven multimodal presentation videos with research grounding, supporting single-speaker, multi-speaker discussion, and interactive question-answering modes.

  3. Narrative-Driven Paper-to-Slide Generation via ArcDeck

    cs.AI 2026-04 unverdicted novelty 6.0

    ArcDeck models paper-to-slide generation as narrative reconstruction using discourse parsing and multi-agent refinement, plus a new ArcBench benchmark, to improve flow and coherence over direct summarization.

  4. DeepSlide: From Artifacts to Presentation Delivery

    cs.AI 2026-04 unverdicted novelty 6.0

    DeepSlide introduces a multi-agent system for full presentation preparation that matches baselines on slide quality but improves narrative flow, pacing, and script synergy via a new dual-scoreboard benchmark.

  5. DECKBench: Benchmarking Multi-Agent Frameworks for Academic Slide Generation and Editing

    cs.AI 2026-02 conditional novelty 6.0

    A benchmark for paper-to-slide generation and multi-turn editing, built from 294 pairs and simulated users, with an editing-evaluation design that is partly circular.

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

    cs.AI 2026-07 unverdicted novelty 5.0

    SPIRE approximates page-level slide personalization by training agents to denoise corrupted slide structures via collaborative RL, claiming a proof of consistency as a surrogate for inverse planning.