State-Inference-Based Prompting for Natural Language Trading with Game NPCs
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 18 references that are in the map. First posted on arXiv 9 Jul 2025.
Builds on
6 of 18 references.
References · 6
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
- 2024Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integrationcited by 22
- 2024AgreeMate: Teaching LLMs to Hagglecited by 5
- 2025LLM-Driven NPCs: Cross-Platform Dialogue System for Games and Social Platformscited by 5
- 2024Leveraging Large Language Models for Active Merchant Non-player Characterscited by 4
Built on by
Not cited yet.