We present a high-dimensional neural network potential (HDNNP) for the martensitic phase of the NiTi shape-memory alloy trained to density functional theory (DFT) data. A central aspect of this work is the systematic validation of the potential with respect to the underlying DFT reference method for key properties governing structural evolution, including equilibrium crystal structures, elastic constants, generalized-stacking fault energies, and vibrational spectra. The HDNNP accurately describes the relative stability of the B19$^\prime$ and B33 phases, including subtle energy differences on the order of meV/atom. The predicted stacking-fault energy landscape is strongly anisotropic and reveals a preferential shear pathway, providing atomistic insight into deformation and twinning mechanisms. Finite-temperature molecular dynamics simulations further enable the investigation of unconstrained structural evolution as a function of temperature. Overall, the developed HDNNP provides a robust basis for atomistic simulations of the complex structural and functional behavior of martensitic NiTi systems containing hundreds of thousands of atoms on nanosecond time scales.
P. Jaroš, Petr Sedlák, Petr Šesták et al.· 0 citations
Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well understood. We study this on fully-observable two-player zero-sum games, which provide ground-truth evaluation: outcomes are determined by the rules, and optimality of individual moves can be computed or approximated, without relying on a judge model. Across model tiers, LLMs play suboptimally in simple games such as tic-tac-toe or Connect Four, and lose to MCTS opponents. Obfuscations that preserve the game tree but rewrite its surface form leave performance largely unchanged, indicating the gap is not fully explained by recall of memorized strategies. Motivated by this performance gap, we introduce an agentic framework enhanced with an experience memory designed for the sequential setting and addressing common challenges of sequential decision-making such as credit assignment. We show that post-game reflection and rule extraction yield measurable improvements on tic-tac-toe without modifying the model weights.
Jakub Rada, Viliam Lisý AI Center, Department of Rehabilitation Science et al.· 0 citations