In this paper we introduce a new model of random spanning trees that we call choice spanning trees, constructed from so-called choice random walks. These are random walks for which each step is chosen from a subset of random options, according to some pre-defined rule. The choice spanning trees are constructed by running a choice modified version of Wilson's algorithm or the Aldous-Broder algorithm on the complete graph. We show that the scaling limits of these choice spanning trees are slight variants of random aggregation trees previously considered by Curien and Haas (2017). Moreover, we show that the loop-erasure of a choice random walk run on the complete graph converges after rescaling to a generalized Rayleigh process, extending a result of Evans, Pitman and Winter (2006). These are all natural extensions of similar results for uniform spanning trees.