用大模型指导进化算法，多目标寻找可合成材料
LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery
- 结合大模型与化学规则生成候选材料
- 在14个真实任务中提升发现成功率和优化质量
- 适合需要多目标平衡的材料研发人员
材料发现需在庞大的化学与结构空间中探索，同时满足多个常冲突的目标。我们提出LLEMA框架，将大语言模型中的科学知识与化学引导的进化规则及记忆增强的优化相结合。每轮迭代中，大模型在明确性能约束下生成晶格指定的候选材料；代理增强的评估器预测理化性质；多目标评分器更新成功/失败记忆以指导后续生成。在涵盖电子、能源、涂层、光学和航空航天的14个真实任务上评估，LLEMA发现的材料兼具化学合理性、热力学稳定性和性能匹配性，相比生成模型和仅用大模型的基线，命中率更高，帕累托前沿质量更优。消融实验验证了规则引导生成、记忆强化和代理预测的重要性。通过强制可合成性与多目标权衡，LLEMA为加速实际材料发现提供了系统性方法。项目网站：https://scientific-discovery.github.io/llema-project/
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。