用AI自主通关宝可梦红版，三智能体闭环决策
PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red
- 三代理系统分工协作：规划、执行、评判形成闭环
- 战斗模块胜率80.8%，仅比人类低6个百分点
- 模型语言能力越强，战斗策略越优，各有独特打法
我们提出PokéAI，首个基于文本的多智能体大语言模型框架，可自主运行并推进《宝可梦红》游戏。系统由三个专用智能体组成——规划、执行与评判，各具独立记忆库、角色与技能。规划智能体作为中枢，生成推进游戏的任务；任务交由执行智能体在游戏环境中完成；任务结束后，评判智能体评估结果以判断目标是否达成。验证完成后，控制权返回规划智能体，构成闭环决策机制。我们首先在执行智能体中开发了战斗模块。结果显示，该战斗AI在50次野生对战中平均胜率为80.8%，仅比经验丰富的真人玩家低6%。此外，我们发现模型的语言能力（以LLM Arena得分衡量）与其战斗表现高度相关，表明语言理解力与战略推理存在深层关联。最后，对游戏日志的分析显示，每个大模型均展现出独特的游戏风格，说明不同模型会发展出个性化的策略行为。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。