arXiv cs.AI· Vidushee Vats, Karun Sharma, Yuxia Wang·· 9 天前AI 评分31
SlideLab：面向听众的科研幻灯片生成与评估框架
SlideLab: Audience-Centered Scientific Slide Generation and Evaluation
AI 导读
SlideLab 是一个免训练的多智能体框架，可从研究论文生成科研演示幻灯片，先规划叙事，再由内容规划、视觉生成、布局优化和事实核查等智能体迭代构建共享幻灯片。
正文 · 原文
Abstract: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.
| Comments: | Update Appendix and add few more ablations, ConfArena architecture |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.30294 [cs.CL] |
| (or arXiv:2609.30294v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.30294 arXiv-issued DOI via DataCite |
Submission history
From: Vidushee Vats [view email]
[v1]
Sun, 13 Sep 2026 10:39:04 UTC (11,019 KB)
[v2]
Thu, 8 Oct 2026 12:07:46 UTC (16,580 KB)
来源：arXiv cs.AI · arxiv.org