Institutional Complementarity in the Governance of Military Artificial Intelligence

Why do fragmented governance arrangements sometimes become organised without producing hierarchy or substantive agreement? This article answers that question through the relationship between the Responsible AI in the Military Domain (REAIM) process and the United Nations General Assembly’s agenda on military AI. Drawing on primary and secondary sources, including elite interviews with diplomats serving at UN missions in New York and Geneva, it traces how REAIM widened international deliberation through consultation, practical guidance, and knowledge exchange, while the General Assembly gave the broader agenda universal political standing, a documentary record, and recurring procedures. Their connection produced a bounded institutional arrangement. REAIM supplied ideas and preparatory resources that entered UN reports, submissions, and deliberation, while negotiated authority remained with states in the General Assembly. The article therefore explains how fragmented governance can develop an organised architecture before states agree on regulatory substance. The article advances research on institutional overlap by identifying procedural connection, political support, and shared capacity as sources of order in contested military technology governance.