Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review
2026-07-10 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors created AutoWorldBuilder, a system that helps build fictional worlds using multiple language models working together. They solved problems like keeping the story ideas consistent, managing lots of information without overload, and automatically checking quality. Their system organizes tasks smartly and reviews ideas to make sure they fit well, leading to high success in creating self-consistent worlds quickly. This approach can also help other complex tasks where many AI agents need to collaborate.
worldbuildinglarge language modelsmulti-agent systemcontext compressionsemantic localityquality assurancetask schedulingconcept networkiterative review
Authors
Jingbo Chen, He Wang, Wei Yuan, Yuqiao Lai, Zhenyan Lu
Abstract
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.