Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis
This work addresses the problem of generating professional-standard media presentations for users in content creation and design, representing an incremental improvement over existing methods.
The paper tackles the challenge of automated high-quality media presentation generation by introducing RCPS, a framework that integrates narrative planning, layout generation, and iterative optimization, significantly outperforming baselines across content, coherence, and design dimensions. It also proposes PREVAL, a preference-based evaluation framework that shows strong correlation with human judgments for assessing presentation quality.
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.