让大模型像人一样玩文字游戏，提升叙事理解与决策自然性。
Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games
- 构建空间与叙事关系地图，学习上下文相关操作。
- 通过反馈迭代优化行为，实现更接近人类的玩法。
- 适合研究人机交互、认知模拟与文本游戏的学者。
互动小说游戏（IF游戏）允许玩家通过自然语言指令进行交互。尽管人工智能代理在该领域取得进展，现有方法仍侧重于特定任务表现，而非对叙事背景和游戏逻辑的人类级理解。本文提出一种受认知科学启发的框架——学习像人类一样玩（LPLH），引导大语言模型系统化学习并游玩IF游戏。该框架包含三大组件：（1）结构化地图构建，用于捕捉空间与叙事关系；（2）动作学习，识别情境适配的指令；（3）反馈驱动的经验分析，持续优化决策。通过与叙事意图和常识约束对齐，LPLH超越纯粹探索策略，实现更可解释、更类人的表现。该方法借鉴人类阅读、理解与回应叙事世界的方式，将IF游戏挑战重新定义为大模型代理的学习问题，为复杂文本环境中的鲁棒、上下文感知游戏提供了新路径。
原文摘要 · Abstract (English)
Interactive Fiction games (IF games) are where players interact through natural language commands. While recent advances in Artificial Intelligence agents have reignited interest in IF games as a domain for studying decision-making, existing approaches prioritize task-specific performance metrics over human-like comprehension of narrative context and gameplay logic. This work presents a cognitively inspired framework that guides Large Language Models (LLMs) to learn and play IF games systematically. Our proposed **L**earning to **P**lay **L**ike **H**umans (LPLH) framework integrates three key components: (1) structured map building to capture spatial and narrative relationships, (2) action learning to identify context-appropriate commands, and (3) feedback-driven experience analysis to refine decision-making over time. By aligning LLMs-based agents' behavior with narrative intent and commonsense constraints, LPLH moves beyond purely exploratory strategies to deliver more interpretable, human-like performance. Crucially, this approach draws on cognitive science principles to more closely simulate how human players read, interpret, and respond within narrative worlds. As a result, LPLH reframes the IF games challenge as a learning problem for LLMs-based agents, offering a new path toward robust, context-aware gameplay in complex text-based environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。