Salvato in:
Dettagli Bibliografici
Autori principali: Wu, Yuyang, Cao, Hanzhong, Chen, Jianhao, Li, Yufei
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.08288
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909988722573312
author Wu, Yuyang
Cao, Hanzhong
Chen, Jianhao
Li, Yufei
author_facet Wu, Yuyang
Cao, Hanzhong
Chen, Jianhao
Li, Yufei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08288
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OpenMic: A Multi-Agent-Based Stand-Up Comedy Generation System
Wu, Yuyang
Cao, Hanzhong
Chen, Jianhao
Li, Yufei
Artificial Intelligence
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.
title OpenMic: A Multi-Agent-Based Stand-Up Comedy Generation System
topic Artificial Intelligence
url https://arxiv.org/abs/2601.08288