用智能代理AI让单人角色扮演更沉浸有趣。
Static Vs. Agentic Game Master AI for Facilitating Solo Role-Playing Experiences
- v2采用多智能体与ReAct框架实现推理与行动
- 相比v1，游戏体验更连贯，沉浸感和好奇心显著提升
- 适合想玩深度互动叙事的玩家或研究者
本文提出一个面向单人角色扮演游戏的游戏主控AI，旨在提供类似《龙与地下城》等多人桌游的互动文本叙事体验。通过设计迭代与实验，开发出两个版本系统：v1采用简化提示工程，v2则引入多智能体架构与ReAct框架，实现推理与行动。对比评估显示，v2作为代理式系统能更好维持游戏连贯性，显著提升模组化程度、沉浸感与好奇心。研究为人工智能驱动的互动小说发展提供了新路径，拓展了单人角色扮演体验的可能性。
原文摘要 · Abstract (English)
This paper presents a game master AI for single-player role-playing games. The AI is designed to deliver interactive text-based narratives and experiences typically associated with multiplayer tabletop games like Dungeons & Dragons. We report on the design process and the series of experiments to improve the functionality and experience design, resulting in two functional versions of the system. While v1 of our system uses simplified prompt engineering, v2 leverages a multi-agent architecture and the ReAct framework to include reasoning and action. A comparative evaluation demonstrates that v2 as an agentic system maintains play while significantly improving modularity and game experience, including immersion and curiosity. Our findings contribute to the evolution of AI-driven interactive fiction, highlighting new avenues for enhancing solo role-playing experiences.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。