Paper Overview
- Field: NLP
- Authors: Ming Yang, Zhiwei Zhang, Jiahang Li
- Published: 2025-05-15
- arXiv: 2505.10892
- Matches strong baselines on artifact quality
- Consistently achieves larger gains on delivery metrics, improving narrative fluency, pacing accuracy, and slide–script coordination
Summary
Presentations are a primary medium for scholarly communication, yet most AI slide generators optimize only the *artifact* — a visually plausible deck — while under-optimizing the *delivery process*: pacing, narrative, and presentation preparation.
DeepSlide is a human-in-the-loop multi-agent system that supports preparing the full presentation process, from requirement elicitation and time-budgeted narrative planning, to evidence-grounded slide–script generation, attention augmentation, and rehearsal support.
Key Components
1. Controllable logical-chain planner with per-node time budgets 2. Lightweight content-tree retriever for grounding 3. Markov-style sequential rendering with style inheritance 4. Sandboxed execution with minimal repair to ensure renderability
Evaluation
The authors introduce a dual-scorecard benchmark that cleanly separates static artifact quality from dynamic delivery performance. Across 20 domains and diverse audiences, DeepSlide:
Original Abstract (excerpt)
> Presentations are a primary medium for scholarly communication, yet most AI slide generators optimize the artifact (a visually plausible deck) while under-optimizing the delivery process (pacing, narrative, and presentation preparation). We present DeepSlide, a human-in-the-loop multi-agent system that supports preparing the full presentation process, from requirement elicitation and time-budgeted narrative planning, to evidence-grounded slide–script generation, attention augmentation, and rehearsal support. DeepSlide integrates (i) a controllable logical-chain planner with per-node time budgets, (ii) a lightweight content-tree retriever for grounding, (iii) Markov-style sequential rendering with style inheritance, and (iv) sandboxed execution with minimal repair to ensure renderability...
---
*Auto-collected on 2026-05-19*