Accelerating Materials Design via LLM-Guided Evolutionary Search
This work accelerates practical materials discovery for domains like electronics and energy, though it is incremental as it builds on existing evolutionary and LLM methods.
The paper tackled the problem of navigating vast chemical and structural spaces for materials discovery by introducing LLEMA, a framework that combines LLM guidance with evolutionary rules and memory-based refinement, achieving higher hit-rates and stronger Pareto fronts than baselines across 14 realistic tasks.
Materials discovery requires navigating vast chemical and structural spaces while satisfying multiple, often conflicting, objectives. We present LLM-guided Evolution for MAterials design (LLEMA), a unified framework that couples the scientific knowledge embedded in large language models with chemistry-informed evolutionary rules and memory-based refinement. At each iteration, an LLM proposes crystallographically specified candidates under explicit property constraints; a surrogate-augmented oracle estimates physicochemical properties; and a multi-objective scorer updates success/failure memories to guide subsequent generations. Evaluated on 14 realistic tasks spanning electronics, energy, coatings, optics, and aerospace, LLEMA discovers candidates that are chemically plausible, thermodynamically stable, and property-aligned, achieving higher hit-rates and stronger Pareto fronts than generative and LLM-only baselines. Ablation studies confirm the importance of rule-guided generation, memory-based refinement, and surrogate prediction. By enforcing synthesizability and multi-objective trade-offs, LLEMA delivers a principled pathway to accelerate practical materials discovery. Code: https://github.com/scientific-discovery/LLEMA