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

arXiv: https://arxiv.org/abs/2609.13718 · HTML: https://mlsanity.com/paper/2609.13718/

## 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.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory](https://mlsanity.com/paper/2305.17144/) (2023)
- [Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education](https://mlsanity.com/paper/2309.14534/) (2023)
- [How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging](https://mlsanity.com/paper/2310.05292/) (2023)
- [Large Language Models and Video Games: A Preliminary Scoping Review](https://mlsanity.com/paper/2403.02613/) (2024)
- [Towards Adaptive Feedback with AI: Comparing the Feedback Quality of LLMs and Teachers on Experimentation Protocols](https://mlsanity.com/paper/2502.12842/) (2025)
- [Characterizing LLM-Empowered Personalized Story-Reading and Interaction for Children: Insights from Multi-Stakeholder Perspectives](https://mlsanity.com/paper/2503.00590/) (2025)
- [Role-Playing Simulation Games using ChatGPT](https://mlsanity.com/paper/2402.09161/) (2024)
- [On Video Game Balancing: Joining Player- and Data-Driven Analytics](https://mlsanity.com/paper/2308.07576/) (2023)
- [How to Align Large Language Models for Teaching English? Designing and Developing LLM based-Chatbot for Teaching English Conversation in EFL, Findings and Limitations](https://mlsanity.com/paper/2409.04987/) (2024)

## 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.