COMIC: Agentic Sketch Comedy Generation
This addresses the challenge of automated creative content production for entertainment, though it appears incremental as it builds on existing agent and LLM methods.
The researchers tackled the problem of automatically generating short comedic videos similar to sketch shows by developing an AI system with agents and LLM critics aligned with viewer preferences, achieving results approaching professional quality and state-of-the-art performance in video generation.
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.