Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909693459300352 |
|---|---|
| author | Xi, Wang Shi, Quan Yu, Tian Peng, Yujie Sun, Jiayi Ren, Mengxing Ding, Zenghui Yao, Ningguang |
| author_facet | Xi, Wang Shi, Quan Yu, Tian Peng, Yujie Sun, Jiayi Ren, Mengxing Ding, Zenghui Yao, Ningguang |
| contents | Automated generation of high-quality media presentations is challenging, requiring robust content extraction, narrative planning, visual design, and overall quality optimization. Existing methods often produce presentations with logical inconsistencies and suboptimal layouts, thereby struggling to meet professional standards. To address these challenges, we introduce RCPS (Reflective Coherent Presentation Synthesis), a novel framework integrating three key components: (1) Deep Structured Narrative Planning; (2) Adaptive Layout Generation; (3) an Iterative Optimization Loop. Additionally, we propose PREVAL, a preference-based evaluation framework employing rationale-enhanced multi-dimensional models to assess presentation quality across Content, Coherence, and Design. Experimental results demonstrate that RCPS significantly outperforms baseline methods across all quality dimensions, producing presentations that closely approximate human expert standards. PREVAL shows strong correlation with human judgments, validating it as a reliable automated tool for assessing presentation quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_13285 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis Xi, Wang Shi, Quan Yu, Tian Peng, Yujie Sun, Jiayi Ren, Mengxing Ding, Zenghui Yao, Ningguang Computation and Language 68T50, 68T07 I.2.7; I.2.11; H.5.2 Automated generation of high-quality media presentations is challenging, requiring robust content extraction, narrative planning, visual design, and overall quality optimization. Existing methods often produce presentations with logical inconsistencies and suboptimal layouts, thereby struggling to meet professional standards. To address these challenges, we introduce RCPS (Reflective Coherent Presentation Synthesis), a novel framework integrating three key components: (1) Deep Structured Narrative Planning; (2) Adaptive Layout Generation; (3) an Iterative Optimization Loop. Additionally, we propose PREVAL, a preference-based evaluation framework employing rationale-enhanced multi-dimensional models to assess presentation quality across Content, Coherence, and Design. Experimental results demonstrate that RCPS significantly outperforms baseline methods across all quality dimensions, producing presentations that closely approximate human expert standards. PREVAL shows strong correlation with human judgments, validating it as a reliable automated tool for assessing presentation quality. |
| title | Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis |
| topic | Computation and Language 68T50, 68T07 I.2.7; I.2.11; H.5.2 |
| url | https://arxiv.org/abs/2507.13285 |