用大模型零样本生成3D地图，自动理解指令并调参。
Zero-shot 3D Map Generation with LLM Agents: A Dual-Agent Architecture for Procedural Content Generation
- 双智能体协作：演员试参数，评论员反馈优化
- 无需训练，直接生成多样且结构合法的3D地图
- 适合游戏/仿真开发，不需懂编程即可设计世界
程序化内容生成（PCG）可算法化创建复杂可定制的世界，但控制流程需精确配置晦涩的技术参数。本文提出一种无需训练的架构，利用大语言模型（LLM）代理实现零样本PCG参数配置。尽管大模型能提供自然语言接口，但现成模型常无法弥合用户抽象指令与严格参数之间的语义鸿沟。系统采用演员-评论家双代理架构，通过迭代推理与配置优化，使生成结果逐步匹配人类设计偏好。我们在多种3D地图生成任务上验证该方法，建立了新的指令遵循基准。实验表明，相比单代理基线，本方法能从自然语言描述中生成多样化且结构有效的环境。结果证明，现成大模型可被有效重用于任意PCG工具的通用代理。通过将负担从模型训练转移到架构推理，本方法为在不进行任务特化微调的情况下掌握复杂软件提供了可扩展框架。
原文摘要 · Abstract (English)
Procedural Content Generation (PCG) offers scalable methods for algorithmically creating complex, customizable worlds. However, controlling these pipelines requires the precise configuration of opaque technical parameters. We propose a training-free architecture that utilizes LLM agents for zero-shot PCG parameter configuration. While Large Language Models (LLMs) promise a natural language interface for PCG tools, off-the-shelf models often fail to bridge the semantic gap between abstract user instructions and strict parameter specifications. Our system pairs an Actor agent with a Critic agent, enabling an iterative workflow where the system autonomously reasons over tool parameters and refines configurations to progressively align with human design preferences. We validate this approach on the generation of various 3D maps, establishing a new benchmark for instruction-following in PCG. Experiments demonstrate that our approach outperforms single-agent baselines, producing diverse and structurally valid environments from natural language descriptions. These results demonstrate that off-the-shelf LLMs can be effectively repurposed as generalized agents for arbitrary PCG tools. By shifting the burden from model training to architectural reasoning, our method offers a scalable framework for mastering complex software without task-specific fine-tuning.
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。