State-Inference-Based Prompting for Natural Language Trading with Game NPCs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916835496034304 |
|---|---|
| author | Kim, Minkyung Kim, Junsik Bae, Hwidong Yang, Woongcheol Park, Sangdon Bae, Sohee |
| author_facet | Kim, Minkyung Kim, Junsik Bae, Hwidong Yang, Woongcheol Park, Sangdon Bae, Sohee |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07203 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | State-Inference-Based Prompting for Natural Language Trading with Game NPCs Kim, Minkyung Kim, Junsik Bae, Hwidong Yang, Woongcheol Park, Sangdon Bae, Sohee Artificial Intelligence 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. |
| title | State-Inference-Based Prompting for Natural Language Trading with Game NPCs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2507.07203 |