Leveraging Large Language Models for Active Merchant Non-player Characters

TL;DR

This paper introduces MART, a framework utilizing large language models to enable active, interactive merchant NPCs in games through improved pricing and communication capabilities.

Contribution

It presents a novel LLM-based merchant NPC framework with modules for appraisal and negotiation, addressing passivity issues in game NPCs.

Findings

Finetuning methods improve NPC activity with smaller LLMs.

Different training methods impact NPC responsiveness.

Irregular LLM responses pose challenges.

Abstract

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.