aiqbench analysis
This research introduces COMIC, a novel agentic framework that leverages LLM-based critics and multi-agent competition to automatically generate high-quality sketch comedy videos. By aligning automated evaluation metrics with real viewer preferences derived from YouTube data, the system demonstrates superior performance over existing baselines in both human and automated assessments. The work represents a significant advancement in applying multi-agent systems and evolutionary computing to creative video generation tasks.
COMIC: Agentic Sketch Comedy Generation
arXiv:2603.11048v2 Announce Type: replace-cross 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.
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.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA); Neural and Evolutionary Computing (cs.NE)
arXiv:2603.11048 [cs.CV]
(or arXiv:2603.11048v2 [cs.CV] for this version)
Full text under the publisher's open licence · 153 words
Related coverage
Build agentic creative workflows with Amazon Quick and fal
AWS · Aug 27, 2026
[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded
Latent Space · Sep 9, 2026
Agentic Synthesis against Counterexample-Supplemented Sketches
arXiv · Jul 20, 2026
Top AI Coding Agents and Development Platforms in 2026: Atoms, Devin, Windsurf, Cursor, Warp, and More Compared
MarkTechPost · Jun 10, 2026