Multi-agent generative AI for concept evaluation: consistency, knowledge integration and human alignment
Proceedings of the Design Society · 2026-08 · 6 · 2453-2462
DOI: 10.1017/pds.2026.10603 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Design Society, online erschienen am 02.07.2026. Verfasst von Mas’udah und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Early-stage concept evaluation is critical for selecting viable designs. This study introduces a multi-agent generative AI framework for assessing concepts across four configurations: AI with retrieval-augmented knowledge, AI without external knowledge, human experts, and a hybrid approach. The findings show that AI panels tend to produce uniform evaluation patterns, while retrieval-augmented knowledge alters rating behaviour without leading to closer alignment with human judgement. Hybrid setting achieved closest alignment, indicating AI is effective when combined with expert interpretation.
Zitieren
APA
Mas’udah, Livotov, P., Kokoschko, B. R., Xu, W., Hendra, I., & Hartmann, N. (2026). Multi-agent generative AI for concept evaluation: consistency, knowledge integration and human alignment. Proceedings of the Design Society, 6, 2453-2462. https://doi.org/10.1017/pds.2026.10603
Vancouver
Mas’udah, Livotov P, Kokoschko BR, Xu W, Hendra I, Hartmann N. Multi-agent generative AI for concept evaluation: consistency, knowledge integration and human alignment. Proceedings of the Design Society. 2026;6:2453-2462. doi:10.1017/pds.2026.10603
BibTeX
@article{Masudah2026,
author = {Mas’udah and Livotov, Pavel and Kokoschko, Björn R. and Xu, Wanyu and Hendra, Immanuel and Hartmann, Niklas},
title = {Multi-agent generative AI for concept evaluation: consistency, knowledge integration and human alignment},
journal = {Proceedings of the Design Society},
year = {2026},
volume = {6},
pages = {2453--2462},
doi = {10.1017/pds.2026.10603}
}
EUVIMED