From testbeds to high-stakes work: a review of Human-AI teaming domains and teaming factors

Human-AI teaming is increasingly being studied in applied and high-stakes settings, yet the evidence remains dispersed across domains, constructs, and research traditions. This fragmentation also limits efforts to connect broader human-AI findings to human-robot teaming (HRT), where embodied systems make issues such as coordination, autonomy management, communication, and safety more immediate in real-world interaction.

To provide a clearer picture of the field, we conducted a PRISMA-guided systematic review with bibliometric analysis of 104 peer-reviewed empirical studies published between 2015 and 2025 and identified through Engineering Village, IEEE Xplore, PubMed, ScienceDirect, and Web of Science.

The review maps where human-AI teaming has been evaluated and what teaming aspects are most frequently examined. Cross-domain and interdisciplinary studies were the largest category, representing broad workplace or team-based investigations not tied to a single industry and instead focused on general collaboration issues such as communication, teamwork, coordination, and coworker interaction. Gaming and entertainment, aviation, military and defense operations, emergency response and public safety, and healthcare also represented substantial portions of the literature. Across studies, performance was the most frequently examined aspect, followed by trust, explainability and transparency, decision-making, and team processes. Bibliometric patterns suggest a shift since 2020 from foundational demonstrations in controlled settings toward applied, higher-stakes contexts where trust dynamics, communication, and ethical accountability more directly shape adoption and sustained performance.

Evidence points to a practical conclusion that human-AI teaming works best when the interaction supports coordination, allowing users to form accurate expectations of the AI, adjust autonomy and delegation across task phases, and use transparency cues that calibrate reliance without adding burden. For HRT, these findings reinforce the importance of shared control, mixed-initiative interaction, and designs that help humans and robots coordinate action over time rather than simply divide functions. We conclude by outlining implications for designing and evaluating human-AI teams as socio-technical systems and for prioritizing longitudinal and in-context studies that capture how teaming evolves over time.