Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review

Researchers introduced AutoWorldBuilder, a multi-agent LLM system for automated fictional worldbuilding that uses hierarchical context compression and iterative review to overcome context explosion and consistency challenges. The system achieved a 95% success rate across 20 tasks, generating 56-103 self-consistent concepts per world with zero conflicts, demonstrating transferable architectural patterns for knowledge-intensive multi-agent LLM applications.

arXiv:2607.09403v1 Announce Type: new 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.