# Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generation

arXiv: https://arxiv.org/abs/2504.18805 · HTML: https://mlsanity.com/paper/2504.18805/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 26 Apr 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 27 of 27)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation](https://mlsanity.com/paper/2205.09853/) (2022)
- [Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks](https://mlsanity.com/paper/2202.10571/) (2022)
- [Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models](https://mlsanity.com/paper/2403.00231/) (2024)
- [A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications](https://mlsanity.com/paper/1804.09635/) (2018)
- [ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation](https://mlsanity.com/paper/2402.04324/) (2024)
- [DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents](https://mlsanity.com/paper/2101.11796/) (2021)
- [Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations](https://mlsanity.com/paper/2304.11267/) (2023)
- [Mora: Enabling Generalist Video Generation via A Multi-Agent Framework](https://mlsanity.com/paper/2403.13248/) (2024)
- [Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols](https://mlsanity.com/paper/2009.14237/) (2020)
- [Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback](https://mlsanity.com/paper/2402.03746/) (2024)
- [StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration](https://mlsanity.com/paper/2411.04925/) (2024)
- [FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces](https://mlsanity.com/paper/2501.12909/) (2025)
- [VideoAgent: Self-Improving Video Generation](https://mlsanity.com/paper/2410.10076/) (2024)
- [Contextual Document Embeddings](https://mlsanity.com/paper/2410.02525/) (2024)
- [A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding](https://mlsanity.com/paper/2305.03668/) (2023)
- [Threads of Subtlety: Detecting Machine-Generated Texts Through Discourse Motifs](https://mlsanity.com/paper/2402.10586/) (2024)
- [GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration](https://mlsanity.com/paper/2412.04440/) (2024)
- [KNOWNET: Guided Health Information Seeking from LLMs via Knowledge Graph Integration](https://mlsanity.com/paper/2407.13598/) (2024)
- [Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation](https://mlsanity.com/paper/2402.14146/) (2024)
- [SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing](https://mlsanity.com/paper/2411.18983/) (2024)
- [ScholaWrite: A Dataset of End-to-End Scholarly Writing Process](https://mlsanity.com/paper/2502.02904/) (2025)
- ["It took me almost 30 minutes to practice this". Performance and Production Practices in Dance Challenge Videos on TikTok](https://mlsanity.com/paper/2008.13040/) (2020)

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

- [From Style Replication to Style Exploration: Enabling Art Style Exploration with Analyze-Experiment-Resituate Framework](https://mlsanity.com/paper/2608.14405/) (2026)

## Abstract (arXiv)

Generating engaging, accurate short-form videos from scientific papers is challenging due to content complexity and the gap between expert authors and readers. Existing end-to-end methods often suffer from factual inaccuracies and visual artifacts, limiting their utility for scientific dissemination. To address these issues, we propose SciTalk, a novel multi-LLM agentic framework, grounding videos in various sources, such as text, figures, visual styles, and avatars. Inspired by content creators' workflows, SciTalk uses specialized agents for content summarization, visual scene planning, and text and layout editing, and incorporates an iterative feedback mechanism where video agents simulate user roles to give feedback on generated videos from previous iterations and refine generation prompts. Experimental evaluations show that SciTalk outperforms simple prompting methods in generating scientifically accurate and engaging content over the refined loop of video generation. Although preliminary results are still not yet matching human creators' quality, our framework provides valuable insights into the challenges and benefits of feedback-driven video generation. Our code, data, and generated videos will be publicly available.