Game Development as Human-LLM Interaction
This addresses the problem of making game development more accessible to gaming enthusiasts, though it is incremental as it builds on existing LLM capabilities for a specific domain.
The paper tackles the problem of game development being inaccessible to non-experts by introducing ChatGE, a system that enables custom game creation through natural language interaction with an LLM, resulting in a case study for poker games with evaluated interaction quality and code correctness.
Game development is a highly specialized task that relies on a complex game engine powered by complex programming languages, preventing many gaming enthusiasts from handling it. This paper introduces the Chat Game Engine (ChatGE) powered by LLM, which allows everyone to develop a custom game using natural language through Human-LLM interaction. To enable an LLM to function as a ChatGE, we instruct it to perform the following processes in each turn: (1) $P_{script}$: configure the game script segment based on the user's input; (2) $P_{code}$: generate the corresponding code snippet based on the game script segment; (3) $P_{utter}$: interact with the user, including guidance and feedback. We propose a data synthesis pipeline based on LLM to generate game script-code pairs and interactions from a few manually crafted seed data. We propose a three-stage progressive training strategy to transfer the dialogue-based LLM to our ChatGE smoothly. We construct a ChatGE for poker games as a case study and comprehensively evaluate it from two perspectives: interaction quality and code correctness.