# Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis

arXiv: https://arxiv.org/abs/2507.13285 · HTML: https://mlsanity.com/paper/2507.13285/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 72 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models](https://mlsanity.com/paper/2406.09403/) (2024)
- [Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement](https://mlsanity.com/paper/2406.11176/) (2024)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents](https://mlsanity.com/paper/2101.11796/) (2021)
- [Direct Multi-Turn Preference Optimization for Language Agents](https://mlsanity.com/paper/2406.14868/) (2024)
- [LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay](https://mlsanity.com/paper/2310.14985/) (2023)
- [Do as We Do, Not as You Think: the Conformity of Large Language Models](https://mlsanity.com/paper/2501.13381/) (2025)
- [D2S: Document-to-Slide Generation Via Query-Based Text Summarization](https://mlsanity.com/paper/2105.03664/) (2021)
- [PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion](https://mlsanity.com/paper/2311.01767/) (2023)
- [On Learning Text Style Transfer with Direct Rewards](https://mlsanity.com/paper/2010.12771/) (2020)
- [Towards Low-Resource Harmful Meme Detection with LMM Agents](https://mlsanity.com/paper/2411.05383/) (2024)
- [Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approach](https://mlsanity.com/paper/2406.06556/) (2024)
- [Rethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty Grading](https://mlsanity.com/paper/2504.11919/) (2025)
- [Automatically Generating Engaging Presentation Slide Decks](https://mlsanity.com/paper/1903.09308/) (2019)
- [Textual-to-Visual Iterative Self-Verification for Slide Generation](https://mlsanity.com/paper/2502.15412/) (2025)

## Built on by (most cited first, 1 of 1)

- [APD-Agents: A Large Language Model-Driven Multi-Agents Collaborative Framework for Automated Page Design](https://mlsanity.com/paper/2511.14101/) (2025)

## Abstract (arXiv)

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.