We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting with character references, the system employs a population of agents loosely based on real production studio roles, structured to optimize the quality and diversity of ideas and outputs through iterative competition, evaluation, and improvement. A key contribution is the introduction of LLM critics aligned with real viewer preferences through the analysis of a corpus of comedy videos on YouTube to automatically evaluate humor. Our experiments show that our framework produces results approaching the quality of professionally produced sketches while demonstrating state-of-the-art performance in video generation.
@article{arxiv.2603.11048,
title = {COMIC: Agentic Sketch Comedy Generation},
author = {Susung Hong and Brian Curless and Ira Kemelmacher-Shlizerman and Steve Seitz},
journal= {arXiv preprint arXiv:2603.11048},
year = {2026}
}