# Pok'eAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red

arXiv: https://arxiv.org/abs/2506.23689 · HTML: https://mlsanity.com/paper/2506.23689/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## 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, 5 of 5)

- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks](https://mlsanity.com/paper/2502.08235/) (2025)
- [BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data](https://mlsanity.com/paper/2410.16491/) (2024)
- [Conditional Imitation Learning for Multi-Agent Games](https://mlsanity.com/paper/2201.01448/) (2022)

## Built on by (most cited first, 1 of 1)

- [Shall We Play a Game? Language Models for Open-ended Wargames](https://mlsanity.com/paper/2509.17192/) (2025)

## Abstract (arXiv)

We introduce Pok'eAI, the first text-based, multi-agent large language model (LLM) framework designed to autonomously play and progress through Pok'emon Red. Our system consists of three specialized agents-Planning, Execution, and Critique-each with its own memory bank, role, and skill set. The Planning Agent functions as the central brain, generating tasks to progress through the game. These tasks are then delegated to the Execution Agent, which carries them out within the game environment. Upon task completion, the Critique Agent evaluates the outcome to determine whether the objective was successfully achieved. Once verification is complete, control returns to the Planning Agent, forming a closed-loop decision-making system. As a preliminary step, we developed a battle module within the Execution Agent. Our results show that the battle AI achieves an average win rate of 80.8% across 50 wild encounters, only 6% lower than the performance of an experienced human player. Furthermore, we find that a model's battle performance correlates strongly with its LLM Arena score on language-related tasks, indicating a meaningful link between linguistic ability and strategic reasoning. Finally, our analysis of gameplay logs reveals that each LLM exhibits a unique playstyle, suggesting that individual models develop distinct strategic behaviors.