2025/07/09 by Minkyung Kim, Kim, Minkyung, Junsik Kim +8
Computer Science · #Algorithmic trading #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #Baseline (sea) #FOS: Computer and information sciences #High-frequency trading #Implementation #Inference #Multimodal Machine Learning Applications #Natural language #State (computer science) #Topic Modeling #Trading strategy #Trustworthiness
paper · pdf · doi:10.48550/arxiv.2507.07203
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/07/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.