Linking AI agent architectures to trust antecedents in human-autonomous teams: a scoping review

The rapid adoption of AI agents is transforming how human teams collaborate in problem-solving across academia, industry, and government. Although AI agents offer promising enhancements to team performance and productivity, trust fundamentally shapes human interactions with technology, influencing the effectiveness and success of human-autonomous teaming (HAT). While there is a wealth of literature on trust between socio-technical relationships, significant gaps persist. In particular, how trust in HAT varies across different agent architectures. This gap limits the ability to identify patterns in existing research, assess the consistency of trust conceptualisations, and understand how methodological choices relate to different agent designs. To address these gaps, this paper systematically maps the current landscape, identifying key bibliometric trends, prevalent agent architectures, and the alignment of trust antecedents with those architectures in recent HAT studies. Our scoping review highlights a lack of clear and systematic links between agent capabilities and the trust factors examined in HAT studies. We emphasise the need for research designs that explore diverse agent roles and team configurations while testing how specific architectures foster particular trust antecedents to strengthen both the validity and applicability of HAT findings.