{"slug": "slidelab-audience-centered-scientific-slide-generation-and-evaluation", "title": "SlideLab: Audience-Centered Scientific Slide Generation and Evaluation", "summary": "SlideLab, a training-free multi-agent framework for generating scientific presentations from research papers, was preferred over both open-source and commercial systems on 77% of papers in a blind human preference study while using roughly 4 times fewer inference tokens than the strongest open-source baseline, according to the arXiv paper arXiv:2609.30294v1. SlideLab plans a presentation narrative and then builds and iteratively refines a shared slide deck using agents for content planning, visual generation, layout refinement, and grounding verification. The paper also introduces ConfArena, an audience-oriented evaluation framework that simulates a conference room and assesses presentations slide by slide, matching human system rankings and detecting injected problems including falsified numbers, degraded figures, dropped slides, and shuffled slide order.", "body_md": "arXiv:2609.30294v1 Announce Type: new \nAbstract: Scientific presentations are more than summaries of research papers. They need to present the work in a coherent sequence, explain the main ideas clearly, and help the audience follow the presentation. We present SlideLab, a training-free multi-agent framework for generating scientific presentations from research papers. SlideLab first plans the presentation narrative, then builds and iteratively refines a shared slide deck using agents for content planning, visual generation, layout refinement, and grounding verification. In a blind human preference study, SlideLab was preferred over both open-source and commercial systems on 77% of papers while using roughly 4 times fewer inference tokens than the strongest open-source baseline. We also introduce ConfArena, an audience-oriented evaluation framework that simulates a conference room and assesses presentations slide by slide. ConfArena matches human system rankings and detects injected presentation problems, including falsified numbers, degraded figures, dropped slides, and shuffled slide order.", "url": "https://wpnews.pro/news/slidelab-audience-centered-scientific-slide-generation-and-evaluation", "canonical_source": "https://arxiv.org/abs/2609.30294", "published_at": "2026-09-28 04:00:00+00:00", "updated_at": "2026-09-28 04:18:24.281790+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "generative-ai"], "entities": ["SlideLab", "ConfArena", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/slidelab-audience-centered-scientific-slide-generation-and-evaluation", "markdown": "https://wpnews.pro/news/slidelab-audience-centered-scientific-slide-generation-and-evaluation.md", "text": "https://wpnews.pro/news/slidelab-audience-centered-scientific-slide-generation-and-evaluation.txt", "jsonld": "https://wpnews.pro/news/slidelab-audience-centered-scientific-slide-generation-and-evaluation.jsonld"}}