Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help

2026-09-12

AI Summary

研究解决了AI在游戏学习中提供支持的问题，通过开发PEARL系统结合语义知识检索与游戏状态匹配来辅助玩家，但玩家偏好现有可视化系统。

Abstract

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.

Problem

• game-based learning
• generative models
• structured game data
• AI support

Innovation

• Retrieval-Augmented Generation (RAG)
• semantic knowledge retrieval
• structural board-state matching
• contextualized scaffolding
• Parallel programming