Saved in:
Bibliographic Details
Main Authors: Hong, Susung, Curless, Brian, Kemelmacher-Shlizerman, Ira, Seitz, Steve
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.11048
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912962019590144
author Hong, Susung
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steve
author_facet Hong, Susung
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steve
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11048
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle COMIC: Agentic Sketch Comedy Generation
Hong, Susung
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steve
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Multiagent Systems
Neural and Evolutionary Computing
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.
title COMIC: Agentic Sketch Comedy Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Multiagent Systems
Neural and Evolutionary Computing
url https://arxiv.org/abs/2603.11048