Game Agent Driven by Free-Form Text Command: Using LLM-based Code Generation and Behavior Branch
This addresses the need for more natural and flexible control in real-time interactive game agents, though it is incremental as it builds on existing LLM and behavior tree technologies.
The paper tackled the problem of game agents being limited to predefined text commands by proposing a system that uses LLM-based code generation to interpret free-form natural language commands into behavior branches, enabling execution in a Pokémon-like game environment with empirical validation showing successful command understanding and execution.
Several attempts have been made to implement text command control for game agents. However, current technologies are limited to processing predefined format commands. This paper proposes a pioneering text command control system for a game agent that can understand natural language commands expressed in free-form. The proposed system uses a large language model (LLM) for code generation to interpret and transform natural language commands into behavior branch, a proposed knowledge expression based on behavior trees, which facilitates execution by the game agent. This study conducted empirical validation within a game environment that simulates a Pokémon game and involved multiple participants. The results confirmed the system's ability to understand and carry out natural language commands, representing a noteworthy in the realm of real-time language interactive game agents. Notice for the use of this material. The copyright of this material is retained by the Japanese Society for Artificial Intelligence (JSAI). This material is published here with the agreement of JSAI. Please be complied with Copyright Law of Japan if any users wish to reproduce, make derivative work, distribute or make available to the public any part or whole thereof. All Rights Reserved, Copyright (C) The Japanese Society for Artificial Intelligence.