哎呀，现在不行：PEARL——基于RAG的游戏支持代理与玩家对AI帮助的期望
Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help
浏览论文内容
中文总结 AI 辅助
针对游戏学习中的AI支持，提出双组件RAG系统PEARL，结合语义检索与结构匹配提供情境化帮助，但评估显示玩家偏好可视化系统，并总结出七个开放设计问题。
中文摘要 AI 辅助
AI驱动的游戏支持代理在基于游戏的学习中展现出前景，然而将生成模型扎根于结构化游戏数据仍然是一个开放的挑战。我们提出了PEARL（并行反思与学习教育代理），一个双组件检索增强生成（RAG）系统，结合语义知识检索与结构棋盘状态匹配，在Parallel——一款用于学习并行编程的益智游戏——中提供情境化支架。PEARL处理两个输入流（自然语言查询和棋盘拓扑），检索游戏操作的概念解释和同伴生成的棋盘状态作为证据：这些能力是仅拥有游戏状态访问权限的标准大型语言模型（LLM）所不具备的。在一项定性评估（N=10）中，将PEARL与现有的基于社区的开放玩家模型（OPM）可视化系统进行比较，参与者在感知有用性上更偏好可视化系统，并报告对PEARL的挫败感更高；十人中有五人最小化或放弃了游戏中的AI工具。主动式交付、泛化回应和信任缺失导致了脱离，而四名参与者的子集发现PEARL的扎根解释在特定情境下（他们主动发起交互时）与可视化互补。我们将PEARL定位为一个已部署的设计探针，其失败模式为AI游戏支持的具体设计议程提供了信息，该议程总结为社区面临的七个开放问题。
英文摘要
AI-powered gameplay support agents hold promise for game-based learning, yet grounding generative models in structured game data remains an open challenge. We present PEARL (Parallel Education Agent for Reflection and Learning), a dual-component Retrieval-Augmented Generation (RAG) system that combines semantic knowledge retrieval with structural board-state matching to deliver contextualized scaffolding in Parallel, a puzzle game for learning parallel programming. PEARL operates on two input streams (natural language queries and board topology), retrieving both conceptual explanations of gameplay moves and peer-generated board states as evidence: capabilities unavailable to a standard Large Language Model (LLM) with game state access alone. In a qualitative evaluation (N=10) comparing PEARL against an existing community-based Open Player Model (OPM) visualization system, participants preferred the visualization system on perceived usefulness and reported higher frustration with PEARL; five of ten minimized or abandoned the AI tool during play. Proactive delivery, generic responses, and trust deficits drove disengagement, while a subset of four participants found PEARL's grounded explanations complementary to visualization in specific contexts where they initiated the interaction. We position PEARL as a deployed design probe whose failure modes inform a concrete design agenda for AI gameplay support, captured as seven open problems for the community.
发表机构
- University of California Santa Cruz（加州大学圣克鲁兹分校）
- University of Central Florida（中佛罗里达大学）
- IT University of Copenhagen（哥本哈根信息技术大学）
机构由 AI 辅助整理，请以论文原文为准。
