The MFEM library [1] is a high-performance C++ library for finite element discretizations that supports a wide range of finite element methods [2] and powers many computational physics and engineering applications across many domains [3]. In this talk we present some of the recent research and development activities in MFEM, focusing on performance portability across leadership-class supercomputing facilities, including exascale supercomputers, as well as new capabilities and functionality, enabling a wider range of applications. This includes work on performance optimizations for GPU architectures, high-order finite element benchmarks and miniapps, scalable unstructured adaptive mesh refinement and matrix-free preconditioning for partially assembled operators that was undertaken as part of the Center for Efficient Exascale Discretizations [4], a co-design center in the US Exascale Computing Project. We will also describe MFEM advancements for large-scale high-order applications, including the 2025 Gordon Bell winner [5], and recent work on solvers for contact problems [6] and differentiable simulations. [1] MFEM Software, https://mfem.org. [2] R. Anderson, J. Andrej, A. Barker, J. Bramwell, J.-S. Camier, J. Cerveny, V. Dobrev, Y. Dudouit, A. Fisher, T. Kolev, W. Pazner, M. Stowell, V. Tomov, I. Akkerman, J. Dahm, D. Medina, and S. Zampini, MFEM: A modular finite element methods library, 2021, https://doi.org/10.1016/j.camwa.2020.06.009. [3] J. Andrej, N. Atallah, J.-P. Backer, J.-S. Camier, D. Copeland, V. Dobrev, Y. Dudouit, T. Duswald, B. Keith, D. Kim, T. Kolev, B. Lazarov, K. Mittal, W. Pazner, S. Petrides, S. Shiraiwa, M. Stowell, and V. Tomov, High-performance finite elements with MFEM, 2024, https://doi.org/10.1177/10943420241261981. [4] Center for Efficient Exascale Discretizations, https://ceed.exascaleproject.org. [5] S. Henneking, S. Venkat, V. Dobrev, J. Camier, T. Kolev, M. Fernando, A. Gabriel, O. Ghattas, Real-time Bayesian inference at extreme scale: A digital twin for tsunami early warning applied to the Cascadia subduction zone, 2025, https://doi.org/10.1145/3712285.3771787. [6] S. Petrides, T. Hartland, T. Kolev, C. Lee, M. Puso, J. Solberg, E. Chin, J. Wang, C. Petra, AMG with Filtering: An Efficient Preconditioner for Interior Point Methods in Large-Scale Contact Mechanics Optimization, in review, 2026, https://arxiv.org/abs/2505.18576.