Year: 2025
Type: conference-paper
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 decisionmaking, existing approaches prioritize taskspecific 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 Learning to Play Like Humans (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 LLMsbased 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.
Authors: Jinming Zhang, Yunfei Long
Institutions: University of Essex, Queen Mary University of London
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4412888537