Inquiry-based modeling plays an important role in science; Science makes progress through formulating and evaluatingquestions, hypothesis, and arguments. The inquiry-based modeling approach also enhances learning about science. How-ever, engaging in modeling requires domain knowledge as well as quantitative skills. The Virtual Ecological ResearchAssistant (VERA) is an interactive learning environment that supports inquiry-based modeling for citizen and studentscientists. VERA provides a visual language for conceptual modeling in the domain of ecology and an AI compiler forautomatic generation of agent-based simulations in the process of constructing, evaluating, and revising the models. Weconducted a pilot study with college-level biology students (N=15) using VERA for modeling ecological phenomena. The2-hour pre- and post-test study demonstrates gains in the learning of ecological content knowledge. We also found that theuse of the Encyclopedia of Life as a source of domain knowledge helped students create more complex models.