PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation

2026-09-22

AI Summary

为解决虚拟角色行为同质化问题，提出PersonaWeaver方法，通过解耦世界构建与行为规范，并使用多样化的道德立场和对话反应库来生成更广泛的行为模式。

Abstract

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 homogenization, we introduce PersonaWeaver, which disentangles world building from behavioral specification and models behavior through setting general, diverse, manually curated banks of moral positions and conversational reactions. This design allows us to test how far LLM(s) can be pushed beyond their default behavioral patterns across settings. Across ten realistic and fantastical settings and three LLM(s), PersonaWeaver produces broader moral and interactional response distributions than prior work. Its guidance also diversifies interpersonal language, response length, and sentiment. It also produces less archetypal combinations of world attributes. Code is available at https://github.com/mqraitem/PersonaWeaver.

Problem

• procedural character generation
• large language models
• behavioral homogeneity
• moral norms

Innovation

• procedural character generation
• diversity in behavior
• moral positions
• conversational reactions
• disentangle world building