This study examines the role of artificial intelligence (AI) in reshaping the ecosystem of digital scholarly communication, drawing on evidence from electronic libraries and large-scale knowledge aggregators. On the basis of an integrative review of recent international and Russian-language scholarship, AI is shown to be gradually evolving into a system-forming infrastructural mechanism across the life cycle of electronic collections, structuring processes of selection, digitisation, metadata creation, storage, and service-oriented resource discovery and access. In parallel, intelligent recommender systems are substantiated as an epistemic mediator influencing the configuration of scholarly reading, the distribution of research attention, and the visibility of peripheral forms of knowledge within the spatial–linguistic architecture of science. It is demonstrated that algorithmic personalisation cannot be reduced to improved search convenience; rather, it participates in constructing relevance norms, linguistic and regional hierarchies, and new regimes for interpreting collections. The effects identified make it possible to conceptualise algorithmic mediation at the intersection of the micro level of research identity and the macro level of the global distribution of scholarly knowledge, while also underscoring the need for reflexive governance of recommender loops in order to preserve epistemic diversity and enhance the transparency of libraries’ digital infrastructures.