Comparing AI and human decision-making mechanisms in daily collaborative experiments

Summary: Artificial intelligence (AI) is trying to catch up with human beings in many aspects. In this track, the potential for replacing human decision-making with AI models, such as large language models (LLMs), has become a topic of considerable debate. To test the performance of AI in daily deci...

Full description

Saved in:
Bibliographic Details
Main Authors: Linghao Wang, Zheyuan Jiang, Chenke Hu, Jun Zhao, Zheng Zhu, Xiqun Chen, Ziyi Wang, Tianming Liu, Guibing He, Yafeng Yin, Der-Horng Lee
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:iScience
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589004225009721
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849471289976160256
author Linghao Wang
Zheyuan Jiang
Chenke Hu
Jun Zhao
Zheng Zhu
Xiqun Chen
Ziyi Wang
Tianming Liu
Guibing He
Yafeng Yin
Der-Horng Lee
author_facet Linghao Wang
Zheyuan Jiang
Chenke Hu
Jun Zhao
Zheng Zhu
Xiqun Chen
Ziyi Wang
Tianming Liu
Guibing He
Yafeng Yin
Der-Horng Lee
author_sort Linghao Wang
collection DOAJ
description Summary: Artificial intelligence (AI) is trying to catch up with human beings in many aspects. In this track, the potential for replacing human decision-making with AI models, such as large language models (LLMs), has become a topic of considerable debate. To test the performance of AI in daily decision-making, we compared humans, LLMs, and reinforcement learning (RL) in a multi-day commute decision-making game. It denotes a collaborative decision-making process where individual and collective outcomes are interdependent. We examined various performance metrics, including overall system results, system convergence progress, individual decision dynamics, and individual decision mechanisms. We find that LLMs exhibit human-like abilities to learn from historical experience and achieve convergence when making daily commute decisions. However, in the context of multi-person collaboration, LLMs still face challenges, such as weak perception of others’ choices, poor group decision-making mechanisms, and a lack of physical knowledge.
format Article
id doaj-art-b954f23ae6ff4234a6e52f2c39c39cc8
institution Kabale University
issn 2589-0042
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series iScience
spelling doaj-art-b954f23ae6ff4234a6e52f2c39c39cc82025-08-20T03:24:52ZengElsevieriScience2589-00422025-06-0128611271110.1016/j.isci.2025.112711Comparing AI and human decision-making mechanisms in daily collaborative experimentsLinghao Wang0Zheyuan Jiang1Chenke Hu2Jun Zhao3Zheng Zhu4Xiqun Chen5Ziyi Wang6Tianming Liu7Guibing He8Yafeng Yin9Der-Horng Lee10Institute of Intelligent Transportation Systems, College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, ChinaInstitute of Intelligent Transportation Systems & Polytechnic Institute, College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, ChinaInstitute of Intelligent Transportation Systems & Polytechnic Institute, College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, ChinaDepartment of Civil and Architectural Engineering and Mechanics, The University of Arizona, Tucson, AZ, USAInstitute of Intelligent Transportation Systems, College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, China; Corresponding authorInstitute of Intelligent Transportation Systems, College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, China; Corresponding authorZhejiang Tranalytic Technology Company, Wenzhou, ChinaDepartment of Civil and Environmental Engineering, University of Michigan, Ann Arbor, MI, USADepartment of Psychology and Behavioral Sciences, Zhejiang University, Hangzhou, ChinaDepartment of Civil and Environmental Engineering, University of Michigan, Ann Arbor, MI, USAZhejiang University–University of Illinois Urbana Champaign Institute, Zhejiang University, Hangzhou, ChinaSummary: Artificial intelligence (AI) is trying to catch up with human beings in many aspects. In this track, the potential for replacing human decision-making with AI models, such as large language models (LLMs), has become a topic of considerable debate. To test the performance of AI in daily decision-making, we compared humans, LLMs, and reinforcement learning (RL) in a multi-day commute decision-making game. It denotes a collaborative decision-making process where individual and collective outcomes are interdependent. We examined various performance metrics, including overall system results, system convergence progress, individual decision dynamics, and individual decision mechanisms. We find that LLMs exhibit human-like abilities to learn from historical experience and achieve convergence when making daily commute decisions. However, in the context of multi-person collaboration, LLMs still face challenges, such as weak perception of others’ choices, poor group decision-making mechanisms, and a lack of physical knowledge.http://www.sciencedirect.com/science/article/pii/S2589004225009721Artificial intelligence applicationsComputing methodologySocial sciences
spellingShingle Linghao Wang
Zheyuan Jiang
Chenke Hu
Jun Zhao
Zheng Zhu
Xiqun Chen
Ziyi Wang
Tianming Liu
Guibing He
Yafeng Yin
Der-Horng Lee
Comparing AI and human decision-making mechanisms in daily collaborative experiments
iScience
Artificial intelligence applications
Computing methodology
Social sciences
title Comparing AI and human decision-making mechanisms in daily collaborative experiments
title_full Comparing AI and human decision-making mechanisms in daily collaborative experiments
title_fullStr Comparing AI and human decision-making mechanisms in daily collaborative experiments
title_full_unstemmed Comparing AI and human decision-making mechanisms in daily collaborative experiments
title_short Comparing AI and human decision-making mechanisms in daily collaborative experiments
title_sort comparing ai and human decision making mechanisms in daily collaborative experiments
topic Artificial intelligence applications
Computing methodology
Social sciences
url http://www.sciencedirect.com/science/article/pii/S2589004225009721
work_keys_str_mv AT linghaowang comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments
AT zheyuanjiang comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments
AT chenkehu comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments
AT junzhao comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments
AT zhengzhu comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments
AT xiqunchen comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments
AT ziyiwang comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments
AT tianmingliu comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments
AT guibinghe comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments
AT yafengyin comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments
AT derhornglee comparingaiandhumandecisionmakingmechanismsindailycollaborativeexperiments