mlsanityData to 7 Oct 2026

COMIC: Agentic Sketch Comedy Generation

arXiv 2603.11048 ↗First posted 11 Mar 2026cs.CV cs.AI cs.CLcited by 2

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 24 of its 42 references that are in the map. First posted on arXiv 11 Mar 2026.

Builds on

24 of 42 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Automated Movie Generation via Multi-Agent CoT Planning10 Mar

Other references · 23

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  2. 2023Large Language Models as Optimizerscited by 830
  3. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 763
  4. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  5. 2015Illuminating search spaces by mapping elitescited by 406
  6. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  7. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 258
  8. 2024StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Textcited by 242
  9. 2023VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planningcited by 138
  10. 2025OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Modelscited by 127
  11. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithmscited by 109
  12. 2025One-Minute Video Generation with Test-Time Trainingcited by 100
11 more
  1. 2023LLM-grounded Video Diffusion Modelscited by 83
  2. 2023Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animatorcited by 74
  3. 2024Vlogger: Make Your Dream A Vlogcited by 70
  4. 2025Captain Cinema: Towards Short Movie Generationcited by 48
  5. 2023DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generationcited by 47
  6. 2024Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generationcited by 35
  7. 2025VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual interventioncited by 33
  8. 2025FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generationcited by 28
  9. 2025VISTA: A Test-Time Self-Improving Video Generation Agentcited by 26
  10. 2026Accelerating Scientific Research with Gemini: Case Studies and Common Techniquescited by 24
  11. 2025MusicInfuser: Making Video Diffusion Listen and Dancecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026A2RD: Agentic Autoregressive Diffusion for Long Video Consistencycited by 6
  2. 2026Agentic Visual Generation: From Generative Models to Agentic Controlcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Jokeasy: Exploring Human-AI Collaboration in Thematic Joke Generation ↗
  2. 2026OpenMic: A Multi-Agent-Based Stand-Up Comedy Generation System
  3. 2025HumorPlanSearch: Structured Planning and HuCoT for Contextual AI Humor
  4. 2024Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
  5. 2026RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar
  6. 2026Yes FLoReNce, I Will Do Better Next Time! Agentic Feedback Reasoning for Humorous Meme Detection
  7. 2024A Robot Walks into a Bar: Can Language Models Serve as Creativity Support Tools for Comedy? An Evaluation of LLMs' Humour Alignment with Comedians
  8. 2026Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges