Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis

TL;DR

This paper introduces RCPS, a comprehensive framework for automated visual narrative synthesis that improves presentation quality through structured planning, adaptive layout, and iterative optimization, validated by a new evaluation framework PREVAL.

Contribution

The paper presents RCPS, a novel multi-component framework for high-quality media presentation generation, and PREVAL, a preference-based evaluation method correlating well with human judgments.

Findings

RCPS outperforms baseline methods in quality metrics

PREVAL correlates strongly with human assessments

Generated presentations closely match professional standards

Abstract

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.