MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (19) · 16316-16324
DOI: 10.1609/aaai.v40i19.38669 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jian Zhang und 8 weiteren Autor:innen.
Abstract (Originalsprache)
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.
Zitieren
APA
Zhang, J., Wang, Z., Wang, Z., Xu, F., Lin, Q., Zhang, L., Mao, R., Cambria, E., & Liu, J. (2026). MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(19), 16316-16324. https://doi.org/10.1609/aaai.v40i19.38669
Vancouver
Zhang J, Wang Z, Wang Z, Xu F, Lin Q, Zhang L, et al. MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(19):16316-16324. doi:10.1609/aaai.v40i19.38669
BibTeX
@article{Zhang2026,
author = {Zhang, Jian and Wang, Zhiyuan and Wang, Zhangqi and Xu, Fangzhi and Lin, Qika and Zhang, Lingling and Mao, Rui and Cambria, Erik and Liu, Jun},
title = {MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {19},
pages = {16316--16324},
doi = {10.1609/aaai.v40i19.38669}
}
EUVIMED