Abstract
Long-distance relationships increasingly rely on AI support, yet how couples conceptualize AI’s appropriate role remains poorly understood. Through semi-structured interviews with 14 individuals in LDRs, we investigate how participants experience, envision, and negotiate boundaries around AI involvement. While participants envisioned AI with contextual intelligence and dyadic understanding, current systems fell short by lacking "warmth", displacing relational accountability, and optimizing for individual rather than shared outcomes. Paradoxically, AI’s "perfection" surfaced the value of visible effort and imperfection: as one participant put it, "clumsiness is love itself." Participants articulated what we term "relational sovereignty", a couple’s right to remain the primary authors of their emotional labor, distinguishing acceptable AI involvement ("post-hoc pattern highlighter") from unacceptable intrusion ("real-time decision-maker"). We contribute design principles shifting AI toward relationship-centered scaffolds that preserve the sovereign work of connecting.

This publication has 29 references indexed in Scilit: