is an open access repository that collects the work of Arts et Métiers ParisTech researchers and makes it freely available over the web where possible. Abstract. In model-driven engineering, model transformations are considered a key element to generate and maintain consistency between related models. Rule-based approaches have become a mature technology and are widely used in different application domains. However, in various scenarios, these solutions still suffer from a number of limitations that stem from their injective and deterministic nature. This article proposes an original approach, based on non-deterministic constraint-based search engines, to define and execute bidirectional model transformations and synchronizations from single specifications. Since these solely rely on basic existing modeling concepts, it does not require the introduction of a dedicated language. We first describe and formally define this model operation, called transformation as search, then describe a proof-of-concept implementation and discuss experiments on a reference use case in software engineering.