Large Language Models enable dynamic game interactions but struggle with rule-governed trading systems. Current implementations suffer from rule violations, such as item hallucinations and calculation errors, that erode player trust. Here, State-Inference-Based Prompting (SIBP) enables reliable trading through autonomous dialogue state inference and context-specific rule adherence. The approach decomposes trading into six states within a unified prompt framework, implementing context-aware item referencing and placeholder-based price calculations. Evaluation across 100 trading dialogues demonstrates >97% state compliance, >95% referencing accuracy, and 99.7% calculation precision. SIBP maintains computational efficiency while outperforming baseline approaches, establishing a practical foundation for trustworthy NPC interactions in commercial games.
Cite
@article{arxiv.2507.07203,
title = {State-Inference-Based Prompting for Natural Language Trading with Game NPCs},
author = {Minkyung Kim and Junsik Kim and Hwidong Bae and Woongcheol Yang and Sangdon Park and Sohee Bae},
journal= {arXiv preprint arXiv:2507.07203},
year = {2025}
}
Comments
9 pages main content, 4 pages appendix, 3 figures. Accepted to the KDD 2025 Workshop on Prompt Optimization