{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/talk-to-your-slides-efficient-slide-editing","title":"Talk to Your Slides: Language-Driven Agents for Efficient Slide Editing","arxiv_id":"2505.11604","date":"2025-05-16","proceeding":null,"authors":["Kyudan Jung","Hojun Cho","Jooyeol Yun","Soyoung Yang","Jaehyeok Jang","Jagul Choo"],"abstract":"Editing presentation slides remains one of the most common and time-consuming tasks faced by millions of users daily, despite significant advances in automated slide generation. Existing approaches have successfully demonstrated slide editing via graphic user interface (GUI)-based agents, offering intuitive visual control. However, such methods often suffer from high computational cost and latency. In this paper, we propose Talk-to-Your-Slides, an LLM-powered agent designed to edit slides %in active PowerPoint sessions by leveraging structured information about slide objects rather than relying on image modality. The key insight of our work is designing the editing process with distinct high-level and low-level layers to facilitate interaction between user commands and slide objects. By providing direct access to application objects rather than screen pixels, our system enables 34.02% faster processing, 34.76% better instruction fidelity, and 87.42% cheaper operation than baselines. To evaluate slide editing capabilities, we introduce TSBench, a human-annotated dataset comprising 379 diverse editing instructions paired with corresponding slide variations in four categories. Our code, benchmark and demos are available at https://anonymous.4open.science/r/Talk-to-Your-Slides-0F4C.","url_abs":"https://arxiv.org/abs/2505.11604v2","url_pdf":"https://arxiv.org/pdf/2505.11604v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"talk-to-your-slides-efficient-slide-editing","repo_url":"https://github.com/KyuDan1/Talk-to-Your-Slides","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"tsbench","name":"TSBench","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.11604","atlas_url":"https://app.syntology.ai/?focus=2505.11604","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}