Surrogate-Gated Generation and Foundation-Model Embeddings for Bayesian Materials Design
For materials scientists and practitioners of closed-loop discovery, this provides a computationally efficient method to reduce oracle calls in generative materials design without sacrificing performance.
This work introduces a surrogate-gated generation framework for Bayesian materials design that uses a cheap probabilistic surrogate (Gaussian process with ORB embeddings) to triage candidate structures from pretrained diffusion models before expensive oracle evaluation. Across three diffusion priors and two targets, the gate matches or exceeds ungated fine-tuning while using only one-fifth of the oracle calls, achieving within ~9% of exhaustive oracle spending.
Closed-loop materials discovery iterates between proposing candidate structures and evaluating their properties, and property evaluation dominates the cost. In the generative variant, a learned prior proposes candidate crystals and a property oracle scores them; we ask whether a cheap probabilistic surrogate can triage the generator's output, and what such a surrogate must do well. Across three architecturally distinct pretrained diffusion priors (MatterGen, CrystalFlow, ADiT) and two targets (room-temperature heat capacity and bulk modulus), we insert a Gaussian process acquisition gate between structure generation and the oracle in an RL-steered generative workflow. The gate matches or exceeds ungated fine-tuning of the generative model while capping oracle calls at a fixed per-cycle budget. Budget-matched ablations isolate the mechanism. At an identical four-call budget, ranking-based selection outperforms arbitrary selection, confirming that the gain comes from the surrogate's choice; the gate comes within $\sim$9\% of exhaustive oracle spending at roughly one-fifth of the calls. A density-functional-theory check of the bulk-modulus discoveries confirms the learned oracle to within 2.5\% on average and the surrogate's ranking of the generated structures at Spearman $ρ= 0.94$. A cross-factorial benchmark of surrogate performance spanning mechanical, electronic, and vibrational properties identifies pretrained ORB embeddings with a Gaussian process as the most reliable combination, which we adopt as the building blocks of the proposed workflow. The complete pipeline is released as open-source software.