PulseAugur
实时 13:14:17
English(EN) Orchestrated Reality: From Role-Play to Living, Playable Game Worlds -- LLM-Driven World Simulation as a Parameterized-Action POMDP

Orchestrated Reality框架使用LLM进行持久化游戏世界模拟

研究人员开发了一个名为“Orchestrated Reality”的框架,使大型语言模型(LLM)能够创建持久化的模拟游戏世界。该系统将游戏世界视为由中央协调代理管理的规范对象,类似于桌面角色扮演游戏中的游戏主持人(GM)。该框架将LLM驱动的游戏世界形式化为一个参数化动作POMDP,其中状态由JSON实体表示,转换由LLM驱动的Plan-Diff-Validate-Apply(PDVA)管道管理。 AI

影响 通过形式化游戏状态和转换,使LLM能够创建持久化的模拟游戏世界。

排序理由 该集群包含一篇描述LLM驱动的世界模拟新框架的学术论文。

在 arXiv cs.MA (Multiagent) 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Yuhang Huang, Chenmiao Li, Chaowei Fang ·

    Orchestrated Reality: From Role-Play to Living, Playable Game Worlds -- LLM-Driven World Simulation as a Parameterized-Action POMDP

    arXiv:2606.16014v1 Announce Type: cross Abstract: Many games rely on storytelling combined with systems that track levelling, NPC behaviour, and consequence simulation; bridging tightly-authored narrative with deeply-simulated worlds -- most acute in sandbox and open-world settin…

  2. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Chaowei Fang ·

    Orchestrated Reality: From Role-Play to Living, Playable Game Worlds -- LLM-Driven World Simulation as a Parameterized-Action POMDP

    Many games rely on storytelling combined with systems that track levelling, NPC behaviour, and consequence simulation; bridging tightly-authored narrative with deeply-simulated worlds -- most acute in sandbox and open-world settings -- has been prohibitively expensive. LLM-driven…