Personality Pairing Improves Human-AI Collaboration

2025-11-17

AI Summary

This study investigates how alignment between AI agent personality traits—operationalized via the Five-Factor Model—and human personality influences collaboration quality, productivity, and task performance. We conduct a large-scale randomized controlled trial in authentic advertising creation, integrating expert human evaluations with real-world deployment on X (formerly Twitter), reaching 1,258 participants and generating nearly 5 million ad impressions. Our analysis systematically assesses multiple personality-matching configurations. We identify, for the first time, a “productivity–performance trade-off”: for instance, pairings of highly open humans with highly conscientious AI agents significantly improve ad quality and collaboration efficiency but do not uniformly optimize all outcome metrics. Moreover, we uncover non-monotonic (jagged) matching effects across cultures and tasks. These findings establish an empirically grounded, testable framework for personality-informed AI design and advance personalized human–AI collaboration theory and practice.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Here we ask how AI agent "personalities" interact with human personalities, and other traits, to shape human-AI collaboration, productivity and performance. To estimate these relationships, we conducted a large-scale preregistered randomized experiment that paired 1,258 participants with AI agents that were 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, and the quality of these ads was evaluated by 1,995 independent human raters as well as in a field experiment conducted on X, which generated nearly 5 million impressions. We found, first, that personality pairing impacted teamwork quality. For example, neurotic AI improved teamwork for agreeable humans but impaired it for conscientious humans. Second, we found productivity effects of personality pairing and a "productivity-performance trade-off" in which certain pairings (e.g., agreeable human with neurotic AI) produced fewer ads but of higher quality. Third, personality pairing influenced ad quality and performance. For example, quality improved when open humans were paired with conscientious AI and when conscientious humans were paired with disagreeable AI. Some of these pairing effects were "jagged" in that they varied across text and visual tasks. For example open humans produced higher quality images but lower quality text when paired with agreeable AI. Pairing effects were also present in other human traits, like country of origin. For example, extroverted AI improved quality for Latin American workers, but degraded quality for East Asian workers. These findings demonstrate that human-AI personality alignment significantly improves collaboration, productivity, and performance and lay a foundation for future research on improving human-AI collaboration through AI personalization.

Problem

• Investigates how AI personality traits interact with human personalities in collaborative tasks
• Examines personality pairing effects on teamwork quality, productivity, and performance outcomes
• Explores how human-AI trait alignment impacts ad creation quality across different demographics

Innovation

• AI agents assigned Big Five personality traits
• Personality pairing tested via large-scale ad creation
• Human-AI alignment improves collaboration and productivity