In this paper, view of the unstable output of a single online sequential learning machine, we propose a selective ensemble algorithm based on glowworm swarm optimization. On the basis of this algorithm, we design an adaptive learning framework of multiple learning machines, which can judge whether to use multiple learning machines for selective ensemble according to the preset threshold. The experimental results show that the proposed approach has higher classification accuracy and generalization performance compared with the basic online sequential extreme learning machine as well as the voting online sequential extreme learning machine.