Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games

TL;DR

This paper introduces a cognitively inspired framework called LPLH that enables Large Language Models to learn and play Interactive Fiction games in a human-like, context-aware manner by integrating structured mapping, action learning, and feedback analysis.

Contribution

The paper presents a novel LPLH framework that guides LLMs to play IF games more interpretably and human-like by incorporating cognitive science principles and structured learning components.

Findings

LPLH improves the interpretability of LLM-based agents in IF games.

The framework enhances decision-making aligned with narrative context.

LPLH demonstrates more human-like gameplay behavior in complex environments.

Abstract

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.