MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jian, Wang, Zhiyuan, Wang, Zhangqi, Xu, Fangzhi, Lin, Qika, Zhang, Lingling, Mao, Rui, Cambria, Erik, Liu, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908646153125888
author Zhang, Jian
Wang, Zhiyuan
Wang, Zhangqi
Xu, Fangzhi
Lin, Qika
Zhang, Lingling
Mao, Rui
Cambria, Erik
Liu, Jun
author_facet Zhang, Jian
Wang, Zhiyuan
Wang, Zhangqi
Xu, Fangzhi
Lin, Qika
Zhang, Lingling
Mao, Rui
Cambria, Erik
Liu, Jun
contents Collaborative reasoning with multiple agents offers the potential for more robust and diverse problem-solving. However, existing approaches often suffer from homogeneous agent behaviors and lack of reflective and rethinking capabilities. We propose Multi-Agent Personality Shaping (MAPS), a novel framework that enhances reasoning through agent diversity and internal critique. Inspired by the Big Five personality theory, MAPS assigns distinct personality traits to individual agents, shaping their reasoning styles and promoting heterogeneous collaboration. To enable deeper and more adaptive reasoning, MAPS introduces a Critic agent that reflects on intermediate outputs, revisits flawed steps, and guides iterative refinement. This integration of personality-driven agent design and structured collaboration improves both reasoning depth and flexibility. Empirical evaluations across three benchmarks demonstrate the strong performance of MAPS, with further analysis confirming its generalizability across different large language models and validating the benefits of multi-agent collaboration.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16905
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning
Zhang, Jian
Wang, Zhiyuan
Wang, Zhangqi
Xu, Fangzhi
Lin, Qika
Zhang, Lingling
Mao, Rui
Cambria, Erik
Liu, Jun
Artificial Intelligence
Collaborative reasoning with multiple agents offers the potential for more robust and diverse problem-solving. However, existing approaches often suffer from homogeneous agent behaviors and lack of reflective and rethinking capabilities. We propose Multi-Agent Personality Shaping (MAPS), a novel framework that enhances reasoning through agent diversity and internal critique. Inspired by the Big Five personality theory, MAPS assigns distinct personality traits to individual agents, shaping their reasoning styles and promoting heterogeneous collaboration. To enable deeper and more adaptive reasoning, MAPS introduces a Critic agent that reflects on intermediate outputs, revisits flawed steps, and guides iterative refinement. This integration of personality-driven agent design and structured collaboration improves both reasoning depth and flexibility. Empirical evaluations across three benchmarks demonstrate the strong performance of MAPS, with further analysis confirming its generalizability across different large language models and validating the benefits of multi-agent collaboration.
title MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning
topic Artificial Intelligence
url https://arxiv.org/abs/2503.16905