Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading
On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 17 of its 30 references that are in the map. First posted on arXiv 28 Oct 2025.
Builds on
17 of 30 references.
Closest ancestors · 1
Same direction, newest first
Other references · 16
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
- 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
- 2024StateFlow: Enhancing LLM Task-Solving through State-Driven Workflowscited by 65
- 2023LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplaycited by 62
- 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
- 2024Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integrationcited by 22
- 2024StateAct: Enhancing LLM Base Agents via Self-prompting and State-trackingcited by 21
4 more
- 2024Player-Driven Emergence in LLM-Driven Game Narrativecited by 16
- 2025LLM-Driven NPCs: Cross-Platform Dialogue System for Games and Social Platformscited by 5
- 2024Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systemscited by 4
- 2024Leveraging Large Language Models for Active Merchant Non-player Characterscited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems
- 2026Agentic Trading: When LLM Agents Meet Financial Markets
- 2026Can Agentic Trading Systems Pay for Their Own Intelligence?
- 2024Large Language Model Agent in Financial Trading: A Survey
- 2026GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models
- 2026QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies
- 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback
- 2024TraderTalk: An LLM Behavioural ABM applied to Simulating Human Bilateral Trading Interactions