Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.15202 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910222535098368 |
|---|---|
| author | Yang, Ming Zhang, Zhiwei Li, Jiahang Liu, Haoseng Cai, Yuzheng Zheng, Weiguo |
| author_facet | Yang, Ming Zhang, Zhiwei Li, Jiahang Liu, Haoseng Cai, Yuzheng Zheng, Weiguo |
| contents | 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. We further introduce a dual-scoreboard benchmark that cleanly separates static artifact quality from dynamic delivery excellence. Across 20 domains and diverse audience profiles, DeepSlide matches strong baselines on artifact quality while consistently achieving larger gains on delivery metrics, improving narrative flow, pacing precision, and slide--script synergy with clearer attention guidance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_15202 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeepSlide: From Artifacts to Presentation Delivery Yang, Ming Zhang, Zhiwei Li, Jiahang Liu, Haoseng Cai, Yuzheng Zheng, Weiguo Artificial Intelligence Computation and Language Information Retrieval I.2.7 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. We further introduce a dual-scoreboard benchmark that cleanly separates static artifact quality from dynamic delivery excellence. Across 20 domains and diverse audience profiles, DeepSlide matches strong baselines on artifact quality while consistently achieving larger gains on delivery metrics, improving narrative flow, pacing precision, and slide--script synergy with clearer attention guidance. |
| title | DeepSlide: From Artifacts to Presentation Delivery |
| topic | Artificial Intelligence Computation and Language Information Retrieval I.2.7 |
| url | https://arxiv.org/abs/2605.15202 |