Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games
This work addresses the challenge of developing robust, context-aware AI agents for text-based games, offering a new learning approach that could benefit researchers in AI and cognitive science, though it appears incremental in adapting existing LLM methods.
The paper tackles the problem of making Large Language Models (LLMs) play Interactive Fiction games more like humans by prioritizing narrative comprehension over task-specific metrics, resulting in a framework that integrates structured map building, action learning, and feedback-driven analysis to achieve more interpretable and human-like performance.
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.