# Can LLMs Generate Behaviors for Embodied Virtual Agents Based on Personality Traits?

## TL;DR

This paper demonstrates that Large Language Models can generate verbal and nonverbal behaviors for virtual agents that accurately reflect specified personality traits, with behaviors perceptible and recognizable by humans.

## Contribution

It introduces a framework using personality prompting in LLMs to produce personality-aligned behaviors for virtual agents, validated through experiments.

## Key findings

- LLMs can generate behaviors reflecting targeted personality traits
- Humans can recognize personality traits from agent behaviors
- Generated behaviors are consistent with intended personality traits

## Abstract

This study proposes a framework that employs personality prompting with Large Language Models to generate verbal and nonverbal behaviors for virtual agents based on personality traits. Focusing on extraversion, we evaluated the system in two scenarios: negotiation and ice breaking, using both introverted and extroverted agents. In Experiment 1, we conducted agent to agent simulations and performed linguistic analysis and personality classification to assess whether the LLM generated language reflected the intended traits and whether the corresponding nonverbal behaviors varied by personality. In Experiment 2, we carried out a user study to evaluate whether these personality aligned behaviors were consistent with their intended traits and perceptible to human observers. Our results show that LLMs can generate verbal and nonverbal behaviors that align with personality traits, and that users are able to recognize these traits through the agents' behaviors. This work underscores the potential of LLMs in shaping personality aligned virtual agents.