COMIC: Agentic Sketch Comedy Generation

Susung Hong, Brian Curless, Ira Kemelmacher-Shlizerman, Steve SeitzOpenReview 2027 · Submission to ICLR 2027 · Withdrawn · OpenReview

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting from character references, the system employs a population of agents loosely modeled on roles in real production studios and structured to optimize the quality and diversity of ideas and outputs through iterative competition, evaluation, and refinement. A key contribution is the introduction of LLM-based critics aligned with real viewer preferences through the analysis of a corpus of comedy videos on YouTube, enabling automatic evaluation of humor. We further propose multi-island relativistic evolution for script improvement, along with script-conditioned rendering critics that perform shot- and video-level tournaments. In both human and automated evaluations, COMIC receives higher scores than agentic and video generation baselines.
BibTeX
@misc{hong2027comic,
  author = {Susung Hong and Brian Curless and Ira Kemelmacher-Shlizerman and Steve Seitz},
  title = {{COMIC: Agentic Sketch Comedy Generation}},
  year = {2027},
  url = {https://openreview.net/forum?id=Rfj9wv4EDR},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2027},
}

Loading related content...

Figure