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, memory-based refinement, and surrogate prediction. By enforcing synthesizability and multi-objective trade-offs, LLEMA provides a principled approach to accelerating practical materials discovery. Project website: https://scientific-discovery.github.io/llema-project/

翻译：材料发现需要在满足多个常相互冲突目标的同时，探索广阔的化学与结构空间。我们提出了LLM引导的材料发现进化框架（LLEMA），这是一个将大语言模型中蕴含的科学知识与基于化学知识的进化规则及基于记忆的优化相结合的统一框架。在每次迭代中，大语言模型在明确的属性约束下提出具有晶体学规格的候选材料；一个基于代理模型增强的评估器估算其物理化学性质；一个多目标评分器则更新成功/失败记忆以指导后续代际。在涵盖电子、能源、涂层、光学和航空航天领域的14项现实任务中进行的评估表明，LLEMA发现的候选材料在化学上合理、热力学稳定且属性符合预期，相较于纯生成模型和纯大语言模型基线，实现了更高的命中率和更优的帕累托前沿质量。消融研究证实了规则引导生成、基于记忆的优化以及代理预测的重要性。通过强制考虑可合成性与多目标权衡，LLEMA为加速实用材料发现提供了一种原则性方法。项目网站：https://scientific-discovery.github.io/llema-project/