GenQuest: An LLM-based Text Adventure Game for Language Learners

2025-10-06

AI Summary

This study addresses the immersive language learning needs of English-as-a-foreign-language (EFL) learners by proposing an adaptive text-adventure game system powered by large language models (LLMs). Methodologically, the system integrates dynamic narrative generation, branching storyline control, and context-aware lexical assistance: it dynamically adjusts textual difficulty based on real-time assessment of learner proficiency, supports interactive plot choices, and delivers on-demand vocabulary explanations with contextual analysis. Its key contribution lies in the tight coupling of adaptive content generation with fine-grained linguistic scaffolding, thereby enabling a personalized, highly interactive language practice environment. Preliminary user studies demonstrate statistically significant vocabulary gains and high user satisfaction. However, findings also highlight persistent challenges—including maintaining narrative coherence, constraining episode length, and extending support to multimodal modalities (e.g., integrated images and text)—pointing to critical directions for future work.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Game Theory and Economic Paradigms: Adversarial Learning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

GenQuest is a generative text adventure game that leverages Large Language Models (LLMs) to facilitate second language learning through immersive, interactive storytelling. The system engages English as a Foreign Language (EFL) learners in a collaborative "choose-your-own-adventure" style narrative, dynamically generated in response to learner choices. Game mechanics such as branching decision points and story milestones are incorporated to maintain narrative coherence while allowing learner-driven plot development. Key pedagogical features include content generation tailored to each learner's proficiency level, and a vocabulary assistant that provides in-context explanations of learner-queried text strings, ranging from words and phrases to sentences. Findings from a pilot study with university EFL students in China indicate promising vocabulary gains and positive user perceptions. Also discussed are suggestions from participants regarding the narrative length and quality, and the request for multi-modal content such as illustrations.

Problem

• Developing an LLM-based game for immersive second language learning
• Generating adaptive story content based on learner proficiency levels
• Providing contextual vocabulary assistance during interactive storytelling

Innovation

• LLM-based generative text adventure for language learning
• Dynamic story generation with branching decision points
• Proficiency-tailored content and in-context vocabulary assistance