发表机构
National University of Defense Technology（国防科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大语言模型应用于世界构建面临的挑战，提出AutoWorldBuilder多智能体协作系统，通过五个组件应对，经实验验证，该系统在世界构建任务中有高成功率，能高效生成自洽概念，其架构模式可推广到其他知识密集型多智能体大语言模型应用。
AI 中文摘要
世界构建是游戏设计和文学创作中的基础任务。大语言模型为自动化内容生成带来新可能，但应用于世界构建面临上下文爆炸、创意多样性与内容一致性的矛盾以及缺乏自动化质量保证等挑战。本文提出AutoWorldBuilder多智能体协作系统，通过结构化概念网络、基于有向无环图的混合批调度器、四层上下文压缩机制、迭代审查系统和技能驱动的智能体架构五个组件应对这些挑战。使用GPT-OSS 120B和DeepSeek v3.2作为大语言模型后端进行的两个实验，在20个不同的世界构建任务中成功率达95.0%。该系统在18 - 31分钟内每个世界生成56 - 103个自洽概念且无冲突交付。其架构模式可应用于更广泛的知识密集型多智能体大语言模型应用。
英文摘要
Worldbuilding, the construction of coherent fictional worlds, is a foundational task in game design and literary creation. Large Language Models (LLMs) offer new possibilities for automated content generation, but their application to worldbuilding faces three challenges: context explosion that grows linearly with the building process, the tension between creative diversity and content consistency, and the absence of automated quality assurance. This paper presents AutoWorldBuilder, a multi-agent collaborative system that addresses these challenges through five integrated components: a structured concept network with conflict detection; a DAG-based hybrid batch scheduler that groups tasks by semantic locality; a four-layer context compression mechanism achieving approximately 90% token reduction; an iterative review system with specialized Auditor agents that improves proposal pass rates from 42% to over 85%; and a skill-driven agent architecture supporting zero-code extension with differentiated temperature configuration. Two experiments across 20 diverse worldbuilding tasks, using GPT-OSS 120B and DeepSeek v3.2 as LLM backends, demonstrate a 95.0% success rate. The system generated 56-103 self-consistent concepts per world in 18-31 minutes with zero-conflict delivery. The architectural patterns validated here, including layer-as-budget compression, semantic-locality scheduling, and separation of generation and review, transfer to the broader class of knowledge-intensive, multi-agent LLM applications.
Comments36 pages, 7 fig
