CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents

TL;DR

CharacterGPT is a framework that dynamically reconstructs and updates character personas in role-playing agents by extracting traits from narrative summaries, improving consistency in generated narratives.

Contribution

It introduces CharacterGPT, a novel method for incrementally updating character personas using chapter-wise summaries, enhancing role-playing agent consistency.

Findings

Effective in maintaining persona consistency across narratives

Improves character trait accuracy via incremental updates

Demonstrates success through personality evaluations and creative tasks

Abstract

The recent introduction of the Assistants API highlights its potential for large language models (LLMs) in role-playing agents (RPA). However, maintaining consistent character personas remains a significant challenge due to variability in information extraction, which frequently omits critical elements such as backstory or interpersonal relationships. To address this limitation, we introduce CharacterGPT, a framework designed to dynamically reconstruct character personas through Character Persona Training (CPT). This approach incrementally updates personas by extracting traits from chapter-wise novel summaries, reflecting the progression of the narrative. Our framework is evaluated through Big Five personality evaluations and creative tasks, in which characters generate original narratives, demonstrating the efficacy of CharacterGPT in preserving persona consistency. The code and results are available at https://github.com/Jeiyoon/charactergpt