AI Navigate

COMIC: Agentic Sketch Comedy Generation

arXiv cs.CV / 3/12/2026

📰 NewsIdeas & Deep AnalysisModels & Research

Key Points

  • The paper proposes a fully automated AI system that generates short comedic videos in a sketch-show style using a population of agents modeled after real production studio roles to iteratively compete, evaluate, and improve ideas.
  • A key contribution is the use of LLM-based critics aligned with viewer preferences, learned by analyzing a corpus of comedy videos on YouTube to automatically evaluate humor.
  • Experiments report that the framework yields results approaching professionally produced sketches and demonstrates state-of-the-art performance in video generation.
  • The work highlights potential implications for how comedic content is produced, evaluated, and iterated, with downstream effects on creative workflows and media production pipelines.

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.