mlsanityData to 7 Oct 2026

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

arXiv 2510.22503 ↗First posted 26 Oct 2025cs.LG cond-mat.mtrl-sci cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

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/

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 27 of its 68 references that are in the map. First posted on arXiv 26 Oct 2025.

Builds on

27 of 68 references.

References · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2024Qwen2.5 Technical Reportcited by 4,713
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  5. 2020Extracting Training Data from Large Language Modelscited by 2,144
  6. 2023Large Language Models as Optimizerscited by 830
  7. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  8. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  9. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 171
  10. 2023Crystal Structure Prediction by Joint Equivariant Diffusioncited by 142
  11. 2022Evolution through Large Modelscited by 131
  12. 2023Large Language Models as Evolutionary Optimizerscited by 122
15 more
  1. 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 117
  2. 2021MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extractioncited by 82
  3. 2023Can GPT-4 Perform Neural Architecture Search?cited by 74
  4. 2023Large Language Models can Learn Rulescited by 66
  5. 2025LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Modelscited by 61
  6. 2024Efficient Evolutionary Search Over Chemical Space with Large Language Modelscited by 59
  7. 2024Large Language Models As Evolution Strategiescited by 57
  8. 2024HoneyComb: A Flexible LLM-Based Agent System for Materials Sciencecited by 56
  9. 2024LLMatDesign: Autonomous Materials Discovery with Large Language Modelscited by 41
  10. 2024Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challengescited by 41
  11. 2024Are LLMs Ready for Real-World Materials Discovery?cited by 40
  12. 2023SoK: Memorization in General-Purpose Large Language Modelscited by 36
  13. 2025LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizerscited by 35
  14. 2024ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedbackcited by 32
  15. 2025Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agentscited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 11.

11 papers.

  1. 2026LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMscited by 7
  2. 2026Open Materials Generation with Inference-Time Reinforcement Learningcited by 6
  3. 2026MADE: Benchmark Environments for Closed-Loop Materials Discoverycited by 5
  4. 2026LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Searchcited by 5
  5. 2026What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Searchcited by 4
  6. 2026SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolutioncited by 1
  7. 2026EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentationcited by 1
  8. 2026My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agentscited by 0
  9. 2026Adaptive Graph-of-Islands Evolution for Automatic Feature Engineering with LLMscited by 0
  10. 2026TRACE: Transition-Aware Residual Control for Multi-Objective Materials Discoverycited by 0
  11. 2026Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop Discoverycited by 0