Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909875493142528 |
|---|---|
| author | Kim, Minkyung Kim, Junsik Yang, Woongcheol Park, Sangdon Bae, Sohee |
| author_facet | Kim, Minkyung Kim, Junsik Yang, Woongcheol Park, Sangdon Bae, Sohee |
| contents | Large Language Models (LLMs) enable dynamic game interactions but fail to follow essential procedural flows in rule-governed trading systems, eroding player trust. This work resolves the core tension between the creative flexibility of LLMs and the procedural demands of in-game trading (browse-offer-review-confirm). To this end, Autoregressive State-Tracking Prompting (ASTP) is introduced, a methodology centered on a strategically orchestrated prompt that compels an LLM to make its state-tracking process explicit and verifiable. Instead of relying on implicit contextual understanding, ASTP tasks the LLM with identifying and reporting a predefined state label from the previous turn. To ensure transactional integrity, this is complemented by a state-specific placeholder post-processing method for accurate price calculations. Evaluation across 300 trading dialogues demonstrates >99% state compliance and 99.3% calculation precision. Notably, ASTP with placeholder post-processing on smaller models (Gemini-2.5-Flash) matches larger models' (Gemini-2.5-Pro) performance while reducing response time from 21.2s to 2.4s, establishing a practical foundation that satisfies both real-time requirements and resource constraints of commercial games. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25014 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading Kim, Minkyung Kim, Junsik Yang, Woongcheol Park, Sangdon Bae, Sohee Artificial Intelligence Large Language Models (LLMs) enable dynamic game interactions but fail to follow essential procedural flows in rule-governed trading systems, eroding player trust. This work resolves the core tension between the creative flexibility of LLMs and the procedural demands of in-game trading (browse-offer-review-confirm). To this end, Autoregressive State-Tracking Prompting (ASTP) is introduced, a methodology centered on a strategically orchestrated prompt that compels an LLM to make its state-tracking process explicit and verifiable. Instead of relying on implicit contextual understanding, ASTP tasks the LLM with identifying and reporting a predefined state label from the previous turn. To ensure transactional integrity, this is complemented by a state-specific placeholder post-processing method for accurate price calculations. Evaluation across 300 trading dialogues demonstrates >99% state compliance and 99.3% calculation precision. Notably, ASTP with placeholder post-processing on smaller models (Gemini-2.5-Flash) matches larger models' (Gemini-2.5-Pro) performance while reducing response time from 21.2s to 2.4s, establishing a practical foundation that satisfies both real-time requirements and resource constraints of commercial games. |
| title | Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.25014 |