This paper is an attempt to design an interaction protocol for a multi-agent learning platform to assist a human community in their task of scientific discovery. Designing tools to assist Scientific Discovery offers a challenging problematic, since the problems studied by scientists are not yet solved, and valid models are not yet available. It is therefore impossible to create a problem solver to simulate a given phenomenon and explain or predict facts. We propose to assist scientists with learning machines considered as adaptive problem solvers, to build interactively a consistent model suited for reasoning, simulating, predicting, and explaining facts. The interaction protocol presented in this paper is based on Angluin's "Learning from Different Teachers" and we extend the original protocol to make it operational to assist scientists solve open problems. The main problem we deal with is that this learning model supposes the existence of teachers having previously solved the problem. These teachers are able to answer the learner's queries whereas this is not the case in the context of Scientific Discovery in which it is only possible to refute a model by finding experimental processes revealing contradictions. Our first contribution is to directly use Angluin's interaction protocol to let a machine learn a program that approximates the theory of a scientist, and to help him improve this theory. Our second contribution is to attenuate Angluin's protocol to take into account a social cognition level during which multiple scientists interact with each other by the means of publications and refutations of rival theories. The program learned by the machine can be included in a publication to avoid false refutations coming from a wrong interpretation of the theory.