# Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation

arXiv: https://arxiv.org/abs/2505.11604 · HTML: https://mlsanity.com/paper/2505.11604/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 16 May 2025.

## Builds on (most cited first, 24 of 24)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [UFO: A UI-Focused Agent for Windows OS Interaction](https://mlsanity.com/paper/2402.07939/) (2024)
- [Does Prompt Formatting Have Any Impact on LLM Performance?](https://mlsanity.com/paper/2411.10541/) (2024)
- [Large Language Models Meet NL2Code: A Survey](https://mlsanity.com/paper/2212.09420/) (2022)
- [Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment](https://mlsanity.com/paper/2402.19085/) (2024)
- [Natural Language to Code Generation in Interactive Data Science Notebooks](https://mlsanity.com/paper/2212.09248/) (2022)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ](https://mlsanity.com/paper/2310.00367/) (2023)
- [If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents](https://mlsanity.com/paper/2401.00812/) (2024)
- [How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations](https://mlsanity.com/paper/2310.10616/) (2023)
- [AutoPresent: Designing Structured Visuals from Scratch](https://mlsanity.com/paper/2501.00912/) (2025)
- [Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering](https://mlsanity.com/paper/2502.06193/) (2025)
- [TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage](https://mlsanity.com/paper/2308.03427/) (2023)
- [Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs](https://mlsanity.com/paper/2502.19411/) (2025)
- [Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming](https://mlsanity.com/paper/2410.12112/) (2024)
- [PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion](https://mlsanity.com/paper/2311.01767/) (2023)
- [Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs](https://mlsanity.com/paper/2401.10065/) (2024)
- [Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs](https://mlsanity.com/paper/2403.13271/) (2024)
- [A Survey on Large Language Models for Automated Planning](https://mlsanity.com/paper/2502.12435/) (2025)
- [PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion](https://mlsanity.com/paper/2403.03788/) (2024)
- [Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs](https://mlsanity.com/paper/2504.20406/) (2025)

## Built on by (most cited first, 11 of 11)

- [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026)
- [PPTArena: A Benchmark for PowerPoint Editing](https://mlsanity.com/paper/2512.03042/) (2025)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs](https://mlsanity.com/paper/2608.02218/) (2026)
- [SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation](https://mlsanity.com/paper/2608.03298/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation](https://mlsanity.com/paper/2608.24103/) (2026)
- [ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback](https://mlsanity.com/paper/2609.00226/) (2026)
- [SlideLab: Audience-Centered Scientific Slide Generation and Evaluation](https://mlsanity.com/paper/2609.30294/) (2026)
- [Beyond Plausibility: Verifiable Fine-Grained Image Editing on Structured Assets](https://mlsanity.com/paper/2610.04381/) (2026)

## Abstract (arXiv)

Editing presentation slides is a frequent yet tedious task, ranging from creative layout design to repetitive text maintenance. While recent GUI-based agents powered by Multimodal LLMs (MLLMs) excel at tasks requiring visual perception, such as spatial layout adjustments, they often incur high computational costs and latency when handling structured, text-centric, or batch processing tasks. In this paper, we propose Talk-to-Your-Slides, a high-efficiency slide editing agent that operates via language-driven structured data manipulation rather than relying on the image modality. By leveraging the underlying object model instead of screen pixels, our approach ensures precise content modification while preserving style fidelity, addressing the limitations of OCR-based visual agents. Our system features a hierarchical architecture that effectively bridges high-level user instructions with low-level execution codes. Experiments demonstrate that for text-centric and formatting tasks, our method enables 34% faster processing, achieves 34% better instruction fidelity, and operates at an 87% lower cost compared to GUI-based baselines. Furthermore, we introduce TSBench, a human-verified benchmark dataset comprising 379 instructions, including a Hard subset designed to evaluate robustness against complex and visually dependent queries. Our code and benchmark are available at https://github.com/KyuDan1/Talk-to-Your-Slides.