OpenMic: A Multi-Agent-Based Stand-Up Comedy Generation System
Yuyang Wu, Hanzhong Cao, Jianhao Chen, Yufei Li
TL;DR
OpenMic tackles long-form Chinese stand-up generation by treating humor as structured reasoning and deploying a multi-agent pipeline to plan, write, deliver, and critique a performance. It fuses AutoGen-based orchestration, RAG grounding, and a JokeWriter fine-tuned via QLoRA to produce coherent text with setup–punchline timing and performance cues, culminating in a narrated video. A dual-dimension quality framework using $Q_r^R$ (retrieval quality) and $Q_r^W$ (writer quality) guides iterative refinement through targeted routing and memory, aided by a blackboard coordination scheme and a Secret Blackboard to manage retrieval noise. The system demonstrates end-to-end production from topic to stage-ready output, highlighting practical potential for culturally grounded automated entertainment and multimodal generation.
Abstract
Chinese stand-up comedy generation goes beyond plain text generation, requiring culturally grounded humor, precise timing, stage-performance cues, and implicit multi-step reasoning. Moreover, commonly used Chinese humor datasets are often better suited for humor understanding and evaluation than for long-form stand-up generation, making direct supervision misaligned with the target task. To address these challenges, we present OpenMic, an end-to-end multi-agent system built on AutoGen that transforms a user-provided life topic into a 3-5 minute Chinese stand-up performance and further produces a narrated comedy video. OpenMic orchestrates multiple specialized agents in a multi-round iterative loop-planning to jointly optimize humor, timing, and performability. To mitigate the dataset-task mismatch, we augment generation with retrieval-augmented generation (RAG) for material grounding and idea expansion, and we fine-tune a dedicated JokeWriter to better internalize stand-up-specific setup-punchline structures and long-range callbacks.