Research

Paper

AI LLM March 11, 2026

COMIC: Agentic Sketch Comedy Generation

Authors

Susung Hong, Brian Curless, Ira Kemelmacher-Shlizerman, Steve Seitz

Abstract

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.

Metadata

arXiv ID: 2603.11048
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-11
Fetched: 2026-03-12 04:21

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.11048v1</id>\n    <title>COMIC: Agentic Sketch Comedy Generation</title>\n    <updated>2026-03-11T17:59:59Z</updated>\n    <link href='https://arxiv.org/abs/2603.11048v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.11048v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.NE'/>\n    <published>2026-03-11T17:59:59Z</published>\n    <arxiv:comment>Project page: https://susunghong.github.io/COMIC/</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Susung Hong</name>\n    </author>\n    <author>\n      <name>Brian Curless</name>\n    </author>\n    <author>\n      <name>Ira Kemelmacher-Shlizerman</name>\n    </author>\n    <author>\n      <name>Steve Seitz</name>\n    </author>\n  </entry>"
}