Abstract: Information loss caused by dimensionality reduction in jet clustering is one of the major limitations for improving the precision of measuring hadronic events at future e−e+ colliders. Such measurements are key for probing (e.g., the nature of Higgs boson) since the hadronic events are dominant in Higgs data. We show that this difficulty could be well addressed by using the machine-learning (ML) techniques at event level. For this purpose, a comparative ML-based study is pursued between jet-level and event-level analyses. We explore how the precision of the benchmark measurements is improved with the assistance of information beyond jet level. As an application of this method, we analyze the precision of measuring the Higgs total width at e−e+ colliders with 5ab−1@240 GeV and its dependence on the detector resolution. We expect that the proposed method can be broadly applied to many other hadronic-event measurements at future e−e+ colliders.