In this commentary, the authors congratulate Professor Alberto Maydeu-Olivares on his article [EJ1023617: "Goodness-of-Fit Assessment of Item Response Theory Models, Measurement: Interdisciplinary Research and Perspectives," this issue] as it provides a much needed overview on the mathematical underpinnings of the theory behind the limited-information-goodness-of-fit testing approach. By focusing on main trends and key ideas, his article offers a rare glimpse at the remarkable theoretical progress that has been made in the area of item response theory (IRT) model evaluation in the last decade or two, without overburdening the readers with all the intricate technicalities. These authors raise three questions as part of their commentary: (1) Can M[superscript 2] or similar fit statistics be used in any other way?; (2) How should RMSEAS be interpreted?; and (3) Is M[superscript 2] the full story? The authors hope that, along with Professor Maydeu-Olivares' article, they may begin a conversation that will lead to a more complete understanding of how IRT models ought to be evaluated in practical settings.