ACL Findings2025
Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games
Jinming Zhang, Yunfei Long
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on9
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
- Interactive Fiction Games: A Colossal AdventureMatthew J. Hausknecht, Prithviraj Ammanabrolu, Marc-Alexandre Côté, Xingdi YuanAAAI 2020 · 242 citations
- Graph Constrained Reinforcement Learning for Natural Language Action SpacesPrithviraj Ammanabrolu, Matthew J. HausknechtICLR 2020 · 138 citations
Related papers
- STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language ModelsShreyas Basavatia, Keerthiram Murugesan, Shivam RatnakarACL Findings 2024 · 5 citations
- Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery GamesDekun Wu, Haochen Shi, Zhiyuan Sun, Bang LiuACL Findings 2024 · 7 citations
- Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement LearningXiaoxiao Guo, Mo Yu, Yupeng Gao, Chuang Gan et al.EMNLP 2020 · 21 citations
- Role-Aware Virtual Agents for Navigational Interaction guided by a Multimodal Large Language ModelMinyoung Kim, Changyang Li, Cuong Nguyen, Lap-Fai YuSIGGRAPH 2026
- The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided ImprovementRuihan Yang, Fanghua Ye, Jian Li, Siyu Yuan et al.NeurIPS 2025 · 21 citations
