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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Jong Inn, Taneja, Maanas, Wang, Qianwen, Kang, Dongyeop
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915259862745088
author Park, Jong Inn
Taneja, Maanas
Wang, Qianwen
Kang, Dongyeop
author_facet Park, Jong Inn
Taneja, Maanas
Wang, Qianwen
Kang, Dongyeop
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18805
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generation
Park, Jong Inn
Taneja, Maanas
Wang, Qianwen
Kang, Dongyeop
Computation and Language
Artificial Intelligence
Machine Learning
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.
title Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generation
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2504.18805