The Drama Machine: Simulating Character Development with LLM Agents

TL;DR

This paper presents a framework using multiple LLM agents to simulate complex character development in dramatic scenarios, enabling nuanced and adaptive narratives through roleplay interactions.

Contribution

Introduces a multi-agent LLM framework for simulating dynamic characters with psychological roles, advancing AI-driven narrative complexity.

Findings

Multi-agent LLM interactions produce nuanced character development.

The framework allows for adaptive narratives over dialogue sequences.

Different modalities of roleplay influence character evolution.

Abstract

This paper explores use of multiple large language model (LLM) agents to simulate complex, dynamic characters in dramatic scenarios. We introduce a drama machine framework that coordinates interactions between LLM agents playing different 'Ego' and 'Superego' psychological roles. In roleplay simulations, this design allows intersubjective dialogue and intra-subjective internal monologue to develop in parallel. We apply this framework to two dramatic scenarios - an interview and a detective story - and compare character development with and without the Superego's influence. Though exploratory, results suggest this multi-agent approach can produce more nuanced, adaptive narratives that evolve over a sequence of dialogical turns. We discuss different modalities of LLM-based roleplay and character development, along with what this might mean for conceptualization of AI subjectivity. The paper concludes by considering how this approach opens possibilities for thinking of the roles of internal conflict and social performativity in AI-based simulation.