Leveraging Large Language Models for Active Merchant Non-player Characters
This work addresses the issue of passive merchant NPCs for game developers and players, but it is incremental as it applies existing LLM techniques to a specific domain.
The paper tackled the problem of passive merchant NPCs in games by addressing pricing and communication limitations, proposing the MART framework based on LLMs, and found that finetuning methods like SFT and KD enable effective use of smaller LLMs for active merchant NPCs, with three irregular cases identified from LLM responses.
We highlight two significant issues leading to the passivity of current merchant non-player characters (NPCs): pricing and communication. While immersive interactions with active NPCs have been a focus, price negotiations between merchant NPCs and players remain underexplored. First, passive pricing refers to the limited ability of merchants to modify predefined item prices. Second, passive communication means that merchants can only interact with players in a scripted manner. To tackle these issues and create an active merchant NPC, we propose a merchant framework based on large language models (LLMs), called MART, which consists of an appraiser module and a negotiator module. We conducted two experiments to explore various implementation options under different training methods and LLM sizes, considering a range of possible game environments. Our findings indicate that finetuning methods, such as supervised finetuning (SFT) and knowledge distillation (KD), are effective in using smaller LLMs to implement active merchant NPCs. Additionally, we found three irregular cases arising from the responses of LLMs.