# Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation

arXiv: https://arxiv.org/abs/2602.14770 · HTML: https://mlsanity.com/paper/2602.14770/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 65 references that are in the map.
- First posted on arXiv 16 Feb 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 18 of 18)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents](https://mlsanity.com/paper/2503.01935/) (2025)
- [Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://mlsanity.com/paper/2402.18272/) (2024)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [Agents' Room: Narrative Generation through Multi-step Collaboration](https://mlsanity.com/paper/2410.02603/) (2024)
- [IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation](https://mlsanity.com/paper/2407.01093/) (2024)
- [Automated Focused Feedback Generation for Scientific Writing Assistance](https://mlsanity.com/paper/2405.20477/) (2024)
- [Small But Funny: A Feedback-Driven Approach to Humor Distillation](https://mlsanity.com/paper/2402.18113/) (2024)
- [Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench](https://mlsanity.com/paper/2507.21476/) (2025)
- [Human Perception of LLM-generated Text Content in Social Media Environments](https://mlsanity.com/paper/2409.06653/) (2024)
- [Who's Laughing Now? An Overview of Computational Humour Generation and Explanation](https://mlsanity.com/paper/2509.21175/) (2025)
- [The Theater Stage as Laboratory: Review of Real-Time Comedy LLM Systems for Live Performance](https://mlsanity.com/paper/2501.08474/) (2025)
- [Feedback Exchange and Online Affinity: A Case Study of Online Fanfiction Writers](https://mlsanity.com/paper/2209.12810/) (2022)
- [Social Story Frames: Contextual Reasoning about Narrative Intent and Reception](https://mlsanity.com/paper/2512.15925/) (2025)

## Built on by (most cited first, 1 of 1)

- [You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful Chinese Online Comments](https://mlsanity.com/paper/2609.04384/) (2026)

## Abstract (arXiv)

Prior work has explored multi-turn interaction and feedback for LLM writing, but evaluations still largely center on prompts and localized feedback, leaving persistent public reception in online communities underexamined. We test whether broadcast community discussion improves stand-up comedy writing in a controlled multi-agent sandbox: in the discussion condition, critic and audience threads are recorded, filtered, stored as social memory, and later retrieved to condition subsequent generations, whereas the baseline omits discussion. Across 50 rounds (250 paired monologues) judged by five expert annotators using A/B preference and a 15-item rubric, discussion wins 75.6% of instances and improves Craft/Clarity (Delta = 0.440) and Social Response (Delta = 0.422), with occasional increases in aggressive humor.