Personality-Driven Decision-Making in LLM-Based Autonomous Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Newsham, Lewis, Prince, Daniel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913770155016192
author Newsham, Lewis
Prince, Daniel
author_facet Newsham, Lewis
Prince, Daniel
contents The embedding of Large Language Models (LLMs) into autonomous agents is a rapidly developing field which enables dynamic, configurable behaviours without the need for extensive domain-specific training. In our previous work, we introduced SANDMAN, a Deceptive Agent architecture leveraging the Five-Factor OCEAN personality model, demonstrating that personality induction significantly influences agent task planning. Building on these findings, this study presents a novel method for measuring and evaluating how induced personality traits affect task selection processes - specifically planning, scheduling, and decision-making - in LLM-based agents. Our results reveal distinct task-selection patterns aligned with induced OCEAN attributes, underscoring the feasibility of designing highly plausible Deceptive Agents for proactive cyber defense strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00727
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Personality-Driven Decision-Making in LLM-Based Autonomous Agents
Newsham, Lewis
Prince, Daniel
Artificial Intelligence
Multiagent Systems
I.2.11; I.2.0
The embedding of Large Language Models (LLMs) into autonomous agents is a rapidly developing field which enables dynamic, configurable behaviours without the need for extensive domain-specific training. In our previous work, we introduced SANDMAN, a Deceptive Agent architecture leveraging the Five-Factor OCEAN personality model, demonstrating that personality induction significantly influences agent task planning. Building on these findings, this study presents a novel method for measuring and evaluating how induced personality traits affect task selection processes - specifically planning, scheduling, and decision-making - in LLM-based agents. Our results reveal distinct task-selection patterns aligned with induced OCEAN attributes, underscoring the feasibility of designing highly plausible Deceptive Agents for proactive cyber defense strategies.
title Personality-Driven Decision-Making in LLM-Based Autonomous Agents
topic Artificial Intelligence
Multiagent Systems
I.2.11; I.2.0
url https://arxiv.org/abs/2504.00727