PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909667000582144 |
|---|---|
| author | Liu, Zihao Sui, Xinhang Song, Yueran Wang, Siwen |
| author_facet | Liu, Zihao Sui, Xinhang Song, Yueran Wang, Siwen |
| contents | We introduce PokéAI, the first text-based, multi-agent large language model (LLM) framework designed to autonomously play and progress through Pokémon 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23689 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red Liu, Zihao Sui, Xinhang Song, Yueran Wang, Siwen Artificial Intelligence Multiagent Systems We introduce PokéAI, the first text-based, multi-agent large language model (LLM) framework designed to autonomously play and progress through Pokémon 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. |
| title | PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2506.23689 |