State-Inference-Based Prompting for Natural Language Trading with Game NPCs

2025/07/09 by Kim, Minkyung, Kim, Junsik, Bae, Hwidong +3
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2507.07203

Abstract

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.

Citations

• LLM-Driven NPCs: Cross-Platform Dialogue System for Games and Social Platforms
• AgreeMate: Teaching LLMs to Haggle
• Leveraging Large Language Models for Active Merchant Non-player Characters
• Generative Agents: Interactive Simulacra of Human Behavior

Related

• Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading
• Leveraging Large Language Models for Active Merchant Non-player Characters
• Augmenting Multi-Agent Communication with State Delta Trajectory
• Evaluating Language Model Agency through Negotiations
• Decoupling Strategy and Generation in Negotiation Dialogues