GameGPT: Multi-agent Collaborative Framework for Game Development
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918136927748096 |
|---|---|
| author | Chen, Dake Zhang, Haoyang Wang, Hanbin Huo, Yunhao Li, Yuzhao Wang, Junjie |
| author_facet | Chen, Dake Zhang, Haoyang Wang, Hanbin Huo, Yunhao Li, Yuzhao Wang, Junjie |
| contents | The large language model (LLM) based agents have demonstrated their capacity to automate and expedite software development processes. In this paper, we focus on game development and propose a multi-agent collaborative framework, dubbed GameGPT, to automate game development. While many studies have pinpointed hallucination as a primary roadblock for deploying LLMs in production, we identify another concern: redundancy. Our framework presents a series of methods to mitigate both concerns. These methods include dual collaboration and layered approaches with several in-house lexicons, to mitigate the hallucination and redundancy in the planning, task identification, and implementation phases. Furthermore, a decoupling approach is also introduced to achieve code generation with better precision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_08067 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | GameGPT: Multi-agent Collaborative Framework for Game Development Chen, Dake Zhang, Haoyang Wang, Hanbin Huo, Yunhao Li, Yuzhao Wang, Junjie Artificial Intelligence The large language model (LLM) based agents have demonstrated their capacity to automate and expedite software development processes. In this paper, we focus on game development and propose a multi-agent collaborative framework, dubbed GameGPT, to automate game development. While many studies have pinpointed hallucination as a primary roadblock for deploying LLMs in production, we identify another concern: redundancy. Our framework presents a series of methods to mitigate both concerns. These methods include dual collaboration and layered approaches with several in-house lexicons, to mitigate the hallucination and redundancy in the planning, task identification, and implementation phases. Furthermore, a decoupling approach is also introduced to achieve code generation with better precision. |
| title | GameGPT: Multi-agent Collaborative Framework for Game Development |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2310.08067 |