让AI在社区讨论中学习笑话创作，效果显著提升。
Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation
- 引入社区讨论作为社会记忆，影响后续笑话生成
- 讨论组胜出75.6%，创意与清晰度提升0.440分
- 适合研究AI社交学习与幽默生成的学者
以往研究关注多轮交互与局部反馈对大模型写作的影响，但大多聚焦于提示词与即时反馈，忽视了在线社区中的公共接受度。本文在受控的多智能体沙盒中测试广播式社区讨论是否能提升单口喜剧创作：实验组记录并存储批评与观众反馈作为社会记忆，用于后续生成；对照组则无讨论。50轮实验（共250段独白）由五位专家评委通过A/B偏好测试和15项评分量表评估，结果显示讨论组在75.6%的对比中胜出，创意与表达清晰度提升Δ=0.440，社会反响得分提升Δ=0.422，偶有攻击性幽默增加。
原文摘要 · Abstract (English)
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 (Δ = 0.440) and Social Response (Δ = 0.422), with occasional increases in aggressive humor.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。