Psychologically Enhanced AI Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Besta, Maciej, Chandran, Shriram, Gerstenberger, Robert, Lindner, Mathis, Chrapek, Marcin, Martschat, Sebastian Hermann, Ghandi, Taraneh, Iff, Patrick, Niewiadomski, Hubert, Nyczyk, Piotr, Müller, Jürgen, Hoefler, Torsten
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914022582910976
author Besta, Maciej
Chandran, Shriram
Gerstenberger, Robert
Lindner, Mathis
Chrapek, Marcin
Martschat, Sebastian Hermann
Ghandi, Taraneh
Iff, Patrick
Niewiadomski, Hubert
Nyczyk, Piotr
Müller, Jürgen
Hoefler, Torsten
author_facet Besta, Maciej
Chandran, Shriram
Gerstenberger, Robert
Lindner, Mathis
Chrapek, Marcin
Martschat, Sebastian Hermann
Ghandi, Taraneh
Iff, Patrick
Niewiadomski, Hubert
Nyczyk, Piotr
Müller, Jürgen
Hoefler, Torsten
contents We introduce MBTI-in-Thoughts, a framework for enhancing the effectiveness of Large Language Model (LLM) agents through psychologically grounded personality conditioning. Drawing on the Myers-Briggs Type Indicator (MBTI), our method primes agents with distinct personality archetypes via prompt engineering, enabling control over behavior along two foundational axes of human psychology, cognition and affect. We show that such personality priming yields consistent, interpretable behavioral biases across diverse tasks: emotionally expressive agents excel in narrative generation, while analytically primed agents adopt more stable strategies in game-theoretic settings. Our framework supports experimenting with structured multi-agent communication protocols and reveals that self-reflection prior to interaction improves cooperation and reasoning quality. To ensure trait persistence, we integrate the official 16Personalities test for automated verification. While our focus is on MBTI, we show that our approach generalizes seamlessly to other psychological frameworks such as Big Five, HEXACO, or Enneagram. By bridging psychological theory and LLM behavior design, we establish a foundation for psychologically enhanced AI agents without any fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04343
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Psychologically Enhanced AI Agents
Besta, Maciej
Chandran, Shriram
Gerstenberger, Robert
Lindner, Mathis
Chrapek, Marcin
Martschat, Sebastian Hermann
Ghandi, Taraneh
Iff, Patrick
Niewiadomski, Hubert
Nyczyk, Piotr
Müller, Jürgen
Hoefler, Torsten
Artificial Intelligence
Computation and Language
Computers and Society
Human-Computer Interaction
Multiagent Systems
We introduce MBTI-in-Thoughts, a framework for enhancing the effectiveness of Large Language Model (LLM) agents through psychologically grounded personality conditioning. Drawing on the Myers-Briggs Type Indicator (MBTI), our method primes agents with distinct personality archetypes via prompt engineering, enabling control over behavior along two foundational axes of human psychology, cognition and affect. We show that such personality priming yields consistent, interpretable behavioral biases across diverse tasks: emotionally expressive agents excel in narrative generation, while analytically primed agents adopt more stable strategies in game-theoretic settings. Our framework supports experimenting with structured multi-agent communication protocols and reveals that self-reflection prior to interaction improves cooperation and reasoning quality. To ensure trait persistence, we integrate the official 16Personalities test for automated verification. While our focus is on MBTI, we show that our approach generalizes seamlessly to other psychological frameworks such as Big Five, HEXACO, or Enneagram. By bridging psychological theory and LLM behavior design, we establish a foundation for psychologically enhanced AI agents without any fine-tuning.
title Psychologically Enhanced AI Agents
topic Artificial Intelligence
Computation and Language
Computers and Society
Human-Computer Interaction
Multiagent Systems
url https://arxiv.org/abs/2509.04343