In recent years, various data-driven methods have been developed in the field of computational mechanics. Within this field, Kirchdoerfer and Ortiz [1] introduced data-driven mechanics, which substitutes traditional material models with data sets containing discrete pairs of stress and strain. The solution to boundary value problems is then found by minimizing a distance between these pairs, denoted material states, and the so-called mechanical states, which fulfill equilibrium and kinematic compatibility. Originally introduced for elasticity, the extension of the approach to inelastic material behavior is a crucial step. In our extension [2] we utilize a history surrogate, which stores essential information of the paths of stress and strain, in combination with a propagator, which updates the history surrogate at the end of each time step. This history surrogate enhances both, the material and the mechanical states, resulting in a framework which preserves the essence of the orignal method. For application related to trusses presented in [3], it is possible to intuitively find suitable candidates for the history surrogat. For two-dimensional problems, this becomes increasingly challenging. By utilizing a neural network as propagator, we can let the network tackle this task autonomously solely based on discrete paths of stress and strain. In this contribution, we first highlight the capabilities of our extension via truss structures, for which we show results for both, a neural network and an intuitive propagator. The implementation of the framework for higher-dimensional spaces is realized through the neural network propagator. Finally, we present results for inelastic material behavior in two dimensionsal settings, address current challenges and explore potential solutions to these challenges. REFERENCES [1] T. Kirchdoerfer and M. Ortiz. Data-driven computational mechanics. Computer Methods in Applied Mechanics and Engineering 304, 81-101, 2016. [2] K. Poelstra, T. Bartel and B. Schweizer. A data‐driven framework for evolutionary problems in solid mechanics. ZAMM‐Journal of Applied Mathematics and Mechanics 103.e202100538, 2023 [3] T. Bartel, M. Harnisch, B. Schweizer and A. Menzel, A data-driven approach for plasticity using history surrogates: Theory and application in the context of truss structures, Computer Methods in Applied Mechanics and Engineering 414, 116138, 2023.