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.
COMIC: Agentic Sketch Comedy Generation
An AI system generates comedic videos using agent-based optimization and LLM critics trained on YouTube comedy data, producing content comparable to professional sketch shows.
- Year
- 2026
- Venue
- arXiv 2026
- Authors
- 4
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2603.11048ARXIV-DEFAULT
- TL;DR
- Semantic Scholar