Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help
On the map: LLM agents and tool use → Reinforcement learning for LLM agents
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 12 of its 55 references that are in the map. First posted on arXiv 12 Sep 2026.
Builds on
12 of 55 references.
Closest ancestors · 1
Same direction, newest first
Other references · 11
- 2023GPT-4 Technical Reportcited by 18,396
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
- 2023Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Educationcited by 39
- 2023How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debuggingcited by 30
- 2024Large Language Models and Video Games: A Preliminary Scoping Reviewcited by 23
- 2025Towards Adaptive Feedback with AI: Comparing the Feedback Quality of LLMs and Teachers on Experimentation Protocolscited by 6
- 2025Characterizing LLM-Empowered Personalized Story-Reading and Interaction for Children: Insights from Multi-Stakeholder Perspectivescited by 4
- 2024Role-Playing Simulation Games using ChatGPTcited by 3
- 2023On Video Game Balancing: Joining Player- and Data-Driven Analyticscited by 2
- 2024How to Align Large Language Models for Teaching English? Designing and Developing LLM based-Chatbot for Teaching English Conversation in EFL, Findings and Limitationscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026GamED.AI: A Hierarchical Multi-Agent Framework for Automated Educational Game Generation
- 2023SPRING: Studying the Paper and Reasoning to Play Games
- 2026GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
- 2026Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
- 2026RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesis
- 2025TextAtari: 100K Frames Game Playing with Language Agents
- 2026From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models
- 2026GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language Agents