Nov 2025· Proceedings of the National Academy of Sciences of the United States of America· Vol 123 35, pp.
e2530627123
· 4 citations· ⚡ 1 influential· 60 references
MedicineComputer Science
TL;DR
The results demonstrate that personality pairing can improve human-AI collaboration and performance and motivate future research on the complex implications of AI personalization for human-AI collaboration, teamwork, and performance.
Abstract
Here we examine how AI agent "personalities" interact with human personalities to shape human-AI collaboration and performance. In a large-scale, preregistered randomized experiment, we paired 1,258 participants with AI agents prompted to exhibit varying levels of the Big Five personality traits. These human-AI teams produced 7,266 display ads for a real think tank, which we evaluated using 1,168 independent human raters, and a field experiment on X that generated nearly 5 million impressions. We found that human and AI personalities individually shaped ad quality and teamwork and that human-AI personality pairings directly influenced ad quality. For example, extraverted humans paired with conscientious AI produced the lowest quality ads, followed by conscientious humans paired with agreeable AI and neurotic humans paired with conscientious AI. In the field experiment, ad quality significantly influenced ad performance, measured by click-through rates and cost-per-click. Together, these results demonstrate that personality pairing can improve human-AI collaboration and performance. They also motivate future research on the complex implications of AI personalization for human-AI collaboration, teamwork, and performance.
Prior research often finds that AI creativity is limited: single systems rarely outperform humans, and human-AI collaboration does not exceed human output. We argue these conclusions underestimate AI's potential because most studies do not allow iterative, multi-agent exchanges that mirror the social processes underpin...
Y. Luan, Luning Sun, YeunJoon Kim et al.· 0 citations
This work proposes A-B-D to infer traits bottom-up from behavioral data (B-data), namely how agents act on their environment and communicate with users, as recorded in existing trajectories, and offers a new lens for understanding AI personality.
Hao-Kai Zhao, Jie Gao, Yunze Xiao et al.· 0 citations
AI assistants are increasingly framed as digital coworkers rather than tools. In immersive settings such as VR, AI embodiment design choices can become salient social signals that shape human–AI interaction. We investigate how such choices influence users’ perceptions of and behavior toward AI coworkers by employing th...
Isabelle Cuber, Tarek Alakmeh, Mary M. Hausfeld et al.· Proceedings of the 14th Nord...· 0 citations
AI assistance can improve performance without improving self-assessment. We report a study (N=366) comparing Human alone and Human+AI performance on reasoning tasks, for which the AI model is benchmarked on the same items. Participants estimated global and block performance and rated confidence in their answers. Human+...
Daniela Fernandes, Michelle Rausch, A. M. Kloft et al.· 0 citations
The rapid increase in generative artificial intelligence (Gen AI) products has revolutionised the interaction between humans and artificial intelligence. However, the conceptualisation, measurement, and performance implications of human-AI interaction in the workplace remain underexplored. This study utilised a grounde...
Ye-Peng Wu, Yuan-Yuan Jiao, Ping Li et al.· Humanities and Social Scienc...· 0 citations
Artificial intelligence systems can produce information that closely resembles real and human-created information, making it difficult to accurately distinguish between synthetic (AI-generated) and non-synthetic content. We explored whether individual differences in attitudes toward AI or one’s history of engagemen...
Tanaka Manhede, Yuliana Fartachuk, S. Martinez et al.· AI & SOCIETY· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 7, 2026
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduSep 30, 2026
Able to defeat top-ranked human players and more efficient than other models, the new system could help decision-makers in military maneuvers or business negotiations.