CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation

Generative modeling has emerged as a promising approach for crystal structure discovery. However, existing LLM-based generative models struggle with low-level atomic precision, while diffusion-based methods fall short in integrating high-level scientific knowledge. As a result, generated structures are often invalid, unstable, or do not possess desirable properties. To address this gap, we propose CrystalReasoner (CrysReas), an end-to-end LLM framework that generates crystal structures from natural language instructions through reasoning and alignment. Before emitting atomic coordinates, CrysReas writes a thinking trace that states the crystallographic symmetry, the local coordination environments and the physical properties of the target structure, so that the textual knowledge a language model already carries is turned into constraints on the coordinates it is about to write. CrysReas then employs reinforcement learning (RL) with a multi-objective, dense reward function to align generation with downstream desired properties such as physical validity, chemical consistency, and thermodynamic stability. For property-conditioned tasks, we design task-specific reward functions and train specialized models for discrete constraints (e.g., space group) and continuous properties (e.g., elasticity, thermal expansion). On the MP-20 benchmark, CrysReas raises the share of generated structures that are stable, unique and novel from $2.5\%$ to $3.7\%$ over the strongest prior language-model baseline re-implemented in the same pipeline, and each of three property specialists improves adherence to its target constraint over the unconditioned model. Our work demonstrates the potential of leveraging thinking traces and RL for generating valid, stable, and property-conditioned crystal structures. Code is available at: https://anonymous.4open.science/r/CrystalReasoner/