SOURCE-LINKED INTELLIGENCE

PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Procedural character generation aims to populate games, simulations, and other virtual worlds with diverse characters. Large language models (LLMs) offer a promising foundation for scaling this task. However, LLM-based procedural character generation remains at an early stage: existing methods either generate characters directly or adapt profiles retrieved from persona banks. As we show, both approaches produce behaviorally homogeneous populations: characters overwhelmingly agree with positive moral norms and respond to questions with helpful, assistant-like reactions. To mitigate this homogen

Read original source ↗ Open in workspace

recordType

paper

region

Global