PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
Hao Zheng, Xinyan Guan, Hao Kong, Wenkai Zhang, Jia Zheng, Weixiang Zhou, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun
摘要
Automatically generating presentations from documents is a challenging task that requires accommodating content quality, visual appeal, and structural coherence. Existing methods primarily focus on improving and evaluating the content quality in isolation, overlooking visual appeal and structural coherence, which limits their practical applicability. To address these limitations, we propose PPTAGENT, which comprehensively improves presentation generation through a two-stage, edit-based approach inspired by human workflows. PPTAGENT first analyzes reference presentations to extract slide-level functional types and content schemas, then drafts an outline and iteratively generates editing actions based on selected reference slides to create new slides. To comprehensively evaluate the quality of generated presentations, we further introduce PPTEVAL, an evaluation framework that assesses presentations across three dimensions: Content, Design, and Coherence. Results demonstrate that PP-TAGENT significantly outperforms existing automatic presentation generation methods across all three dimensions. 1
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper12
- Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic PresentationsChengzhi Liu, Yuzhe YANG, Kaiwen Zhou, Zhen Zhang 等ICLR 2026 · 被引用 14 次
- PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster GenerationJiho Choi, Seojeong Park, Seongjong Song, Hyunjung ShimACL 2026 · 被引用 5 次
- StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative FeedbackHongbo Ma, Fei Shen, Hongbin Xu, Xiaoce Wang 等AAAI 2026 · 被引用 4 次
- Preacher: Paper-to-Video Agentic SystemJingwei Liu, Ling Yang, Hao Luo, Fan Wang 等ICCV 2025 · 被引用 3 次
- SlideTailor: Personalized Presentation Slide Generation for Scientific PapersWenzheng Zeng, Mingyu Ouyang, Langyuan Cui, Hwee Tou NgAAAI 2026 · 被引用 3 次
它引用的顶会 Paper11
- Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng 等SOSP 2023 · 被引用 1,016 次
- G-Eval: NLG Evaluation using Gpt-4 with Better Human AlignmentYang Liu, Dan Iter, Yichong Xu, Shuohang Wang 等EMNLP 2023 · 被引用 549 次
- LayoutGPT: Compositional Visual Planning and Generation with Large Language ModelsWeixi Feng, Wanrong Zhu, Tsu-Jui Fu, Varun Jampani 等NeurIPS 2023 · 被引用 462 次
- Executable Code Actions Elicit Better LLM AgentsXingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang 等ICML 2024 · 被引用 436 次
- Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-Based RetrofittingXinyan Guan, Yanjiang Liu, Hongyu Lin, Yaojie Lu 等AAAI 2024 · 被引用 127 次
相关 Paper
- PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint TasksApurva Gandhi, Vishwas Suryanarayanan, Raja Anwar, Firoz Shaik 等ICML 2026 · 被引用 3 次
- From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and EditingJingxuan Wei, Cheng Tan, Qi Chen, Gaowei Wu 等CVPR 2025
- SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document UnderstandingYiqiao Jin, Rachneet Kaur, Zhen Zeng, Sumitra Ganesh 等ACL 2026 · 被引用 1 次
- PosterAgent: Agentic Poster Generation via Stage-Aware Reinforcement LearningZhuocheng Yu, Feng Zhang, Sujian Li, Kai JiaICML 2026
- PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision ModelsMingde Yao, Zhiyuan You, King-Man Tam, Menglu Wang 等ICML 2026
