[2510.22503] LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery

Computer Science > Machine Learning arXiv:2510.22503 (cs) [Submitted on 26 Oct 2025 (v1), last revised 5 Mar 2026 (this version, v2)] Title:LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery Authors:Nikhil Abhyankar, Sanchit Kabra, Saaketh Desai, Chandan K. Reddy View a PDF of the paper titled LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery, by Nikhil Abhyankar and 3 other authors View PDF HTML (experimental) Abstract:Materials discovery requires navigating vast chemical and structural spaces while satisfying multiple, often conflicting, objectives. We present LLM-guided Evolution for MAterials discovery (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 that span electronics, energy, coatings, optics, and aerospace, LLEMA discovers candidates that are chemically plausible, thermodynamically stable, and property-aligned, achieving higher hit rates and improved Pareto front quality relative to generative and LLM-only baselines. Ablation studies confirm the importance of rule-guided generation, memo...