{"type":"ScholarlyArticle","title":"Leveraging Large Language Models for Active Merchant Non-player Characters","authors":[{"name":"Byungjun Kim","slug":"byungjun-kim","given":"Byungjun","family":"Kim","affiliation":""},{"name":"Minju Kim","slug":"minju-kim","given":"Minju","family":"Kim","affiliation":""},{"name":"Dayeon Seo","slug":"dayeon-seo","given":"Dayeon","family":"Seo","affiliation":""},{"name":"Bugeun Kim","slug":"bugeun-kim","given":"Bugeun","family":"Kim","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/1123","url":"https://ijcai.org/proceedings/2025/1123","pdf":"https://ijcai.org/proceedings/2025/1123.pdf","markdown":"https://ijcai.org/proceedings/2025/1123.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1123","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"AI, Arts & Creativity","track":"AI, Arts & Creativity","number":1123,"pages":{"first":10108,"last":10116},"keywords":["Application domains: Games","Methods and resources: Applications and software frameworks"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}