GameGPT: Multi-agent Collaborative Framework for Game Development

2023/10/12 by Chen, Dake, Zhang, Haoyang, Wang, Hanbin +3 · 7 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2310.08067

Abstract

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.

Cited by

• The Era of Agentic Organization: Learning to Organize with Language Models
• The FM Agent
• V-GameGym: Visual Game Generation for Code Large Language Models
• FAIRGAMER: Evaluating Biases in the Application of Large Language Models to Video Games
• Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMs
• Communicative Agents for Slideshow Storytelling Video Generation based on LLMs
• Multi-Agent Game Generation and Evaluation via Audio-Visual Recordings

Related

• MindAgent: Emergent Gaming Interaction
• A Survey on Large Language Model-Based Game Agents
• Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game
• GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games
• Diamonds in the rough: Transforming SPARCs of imagination into a game concept by leveraging medium sized LLMs