PDE-State Conditioning for Learned Optimization Using Physics-Informed Neural Networks A new arXiv paper (2611.25185v1) introduces a PDE-state-conditioned learned optimizer for physics-informed neural networks that improves relative-L2, L1, solution MSE, and physics MSE over both Adam and an unconditioned learned optimizer on the Linear Advection, KdV, and Burgers equations. The optimizer observes an 11-dimensional PDE state capturing operator structure, residual geometry, and short-horizon update response, and applies it through bounded feature-wise modulation; repeated design studies identified the compact residual-geometry state G2 and bounded FiLM as the strongest overall choices tested. arXiv:2611.25185v1 Announce Type: new Abstract: Physics-informed neural network PINN optimization depends on global properties of the underlying PDE and how the physics residual evolves across the domain. Standard optimizers such as Adam use fixed gradient-based statistics, while learned PINN optimizers replace the fixed rule with a learned update built from local parameters and optimization-history features. However, none explicitly use PDE-level information. We study two coupled design questions: what PDE-level information should a learned optimizer observe, and how should that information influence its update? We introduce an 11-dimensional PDE state-capturing operator structure, residual geometry, and short-horizon update response, and use it to condition a structured meta-learned optimizer through bounded feature-wise modulation. Repeated design studies identify the compact residual-geometry state G2 and bounded FiLM as the strongest overall choices among those tested. The resulting PDE-State-conditioned optimizer improves all evaluation metrics relative-L2, L1, solution MSE, and physics MSE over Adam and the unconditioned learned optimizer on Linear Advection, KdV, and Burgers.