Creativity in LLM-based Multi-Agent Systems: A Survey
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913861338136576 |
|---|---|
| author | Lin, Yi-Cheng Chen, Kang-Chieh Li, Zhe-Yan Wu, Tzu-Heng Wu, Tzu-Hsuan Chen, Kuan-Yu Lee, Hung-yi Chen, Yun-Nung |
| author_facet | Lin, Yi-Cheng Chen, Kang-Chieh Li, Zhe-Yan Wu, Tzu-Heng Wu, Tzu-Hsuan Chen, Kuan-Yu Lee, Hung-yi Chen, Yun-Nung |
| contents | Large language model (LLM)-driven multi-agent systems (MAS) are transforming how humans and AIs collaboratively generate ideas and artifacts. While existing surveys provide comprehensive overviews of MAS infrastructures, they largely overlook the dimension of \emph{creativity}, including how novel outputs are generated and evaluated, how creativity informs agent personas, and how creative workflows are coordinated. This is the first survey dedicated to creativity in MAS. We focus on text and image generation tasks, and present: (1) a taxonomy of agent proactivity and persona design; (2) an overview of generation techniques, including divergent exploration, iterative refinement, and collaborative synthesis, as well as relevant datasets and evaluation metrics; and (3) a discussion of key challenges, such as inconsistent evaluation standards, insufficient bias mitigation, coordination conflicts, and the lack of unified benchmarks. This survey offers a structured framework and roadmap for advancing the development, evaluation, and standardization of creative MAS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21116 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Creativity in LLM-based Multi-Agent Systems: A Survey Lin, Yi-Cheng Chen, Kang-Chieh Li, Zhe-Yan Wu, Tzu-Heng Wu, Tzu-Hsuan Chen, Kuan-Yu Lee, Hung-yi Chen, Yun-Nung Human-Computer Interaction Artificial Intelligence Computation and Language Large language model (LLM)-driven multi-agent systems (MAS) are transforming how humans and AIs collaboratively generate ideas and artifacts. While existing surveys provide comprehensive overviews of MAS infrastructures, they largely overlook the dimension of \emph{creativity}, including how novel outputs are generated and evaluated, how creativity informs agent personas, and how creative workflows are coordinated. This is the first survey dedicated to creativity in MAS. We focus on text and image generation tasks, and present: (1) a taxonomy of agent proactivity and persona design; (2) an overview of generation techniques, including divergent exploration, iterative refinement, and collaborative synthesis, as well as relevant datasets and evaluation metrics; and (3) a discussion of key challenges, such as inconsistent evaluation standards, insufficient bias mitigation, coordination conflicts, and the lack of unified benchmarks. This survey offers a structured framework and roadmap for advancing the development, evaluation, and standardization of creative MAS. |
| title | Creativity in LLM-based Multi-Agent Systems: A Survey |
| topic | Human-Computer Interaction Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2505.21116 |