Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies

TL;DR

This study investigates how human personality traits and AI design features influence imperfect human-AI interactions through simulations and human experiments, revealing context-dependent impacts especially of AI transparency.

Contribution

It compares simulated and real human interactions to identify how AI attributes and human traits jointly affect interaction outcomes in different scenarios.

Findings

AI transparency significantly impacts human-AI interaction outcomes.

Personality traits influence simulated interactions more than real ones.

Scenario type affects the relative importance of AI and human attributes.

Abstract

AI design characteristics and human personality traits each impact the quality and outcomes of human-AI interactions. However, their relative and joint impacts are underexplored in imperfectly cooperative scenarios, where people and AI only have partially aligned goals and objectives. This study compares a purely simulated dataset comprising 2,000 simulations and a parallel human subjects experiment involving 290 human participants to investigate these effects across two scenario categories: (1) hiring negotiations between human job candidates and AI hiring agents; and (2) human-AI transactions wherein AI agents may conceal information to maximize internal goals. We examine user Extraversion and Agreeableness alongside AI design characteristics, including Adaptability, Expertise, and chain-of-thought Transparency. Our causal discovery analysis extends performance-focused evaluations by integrating scenario-based outcomes, communication analysis, and questionnaire measures. Results reveal divergences between purely simulated and human study datasets, and between scenario types. In simulation experiments, personality traits and AI attributes were comparatively influential. Yet, with actual human subjects, AI attributes -- particularly transparency -- were much more impactful. We discuss how these divergences vary across different interaction contexts, offering crucial insights for the future of human-centered AI agents.