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

arXiv: https://arxiv.org/abs/2510.22503 · HTML: https://mlsanity.com/paper/2510.22503/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 68 references that are in the map.
- First posted on arXiv 26 Oct 2025.

## Builds on (most cited first, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Crystal Diffusion Variational Autoencoder for Periodic Material Generation](https://mlsanity.com/paper/2110.06197/) (2021)
- [Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules](https://mlsanity.com/paper/1906.00957/) (2019)
- [Crystal Structure Prediction by Joint Equivariant Diffusion](https://mlsanity.com/paper/2309.04475/) (2023)
- [Evolution through Large Models](https://mlsanity.com/paper/2206.08896/) (2022)
- [LLM-SR: Scientific Equation Discovery via Programming with Large Language Models](https://mlsanity.com/paper/2404.18400/) (2024)
- [Large Language Models as Evolutionary Optimizers](https://mlsanity.com/paper/2310.19046/) (2023)
- [MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extraction](https://mlsanity.com/paper/2109.15290/) (2021)
- [Can GPT-4 Perform Neural Architecture Search?](https://mlsanity.com/paper/2304.10970/) (2023)
- [LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models](https://mlsanity.com/paper/2504.10415/) (2025)
- [Large Language Models can Learn Rules](https://mlsanity.com/paper/2310.07064/) (2023)
- [Efficient Evolutionary Search Over Chemical Space with Large Language Models](https://mlsanity.com/paper/2406.16976/) (2024)
- [Large Language Models As Evolution Strategies](https://mlsanity.com/paper/2402.18381/) (2024)
- [HoneyComb: A Flexible LLM-Based Agent System for Materials Science](https://mlsanity.com/paper/2409.00135/) (2024)
- [LLMatDesign: Autonomous Materials Discovery with Large Language Models](https://mlsanity.com/paper/2406.13163/) (2024)
- [Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges](https://mlsanity.com/paper/2412.11427/) (2024)
- [Are LLMs Ready for Real-World Materials Discovery?](https://mlsanity.com/paper/2402.05200/) (2024)
- [LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers](https://mlsanity.com/paper/2503.14434/) (2025)
- [SoK: Memorization in General-Purpose Large Language Models](https://mlsanity.com/paper/2310.18362/) (2023)
- [ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback](https://mlsanity.com/paper/2402.10980/) (2024)
- [Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents](https://mlsanity.com/paper/2501.13299/) (2025)

## Built on by (most cited first, 13 of 13)

- [LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs](https://mlsanity.com/paper/2605.24043/) (2026)
- [Open Materials Generation with Inference-Time Reinforcement Learning](https://mlsanity.com/paper/2602.00424/) (2026)
- [MADE: Benchmark Environments for Closed-Loop Materials Discovery](https://mlsanity.com/paper/2601.20996/) (2026)
- [LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search](https://mlsanity.com/paper/2606.25039/) (2026)
- [What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search](https://mlsanity.com/paper/2604.19440/) (2026)
- [SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution](https://mlsanity.com/paper/2605.15308/) (2026)
- [EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation](https://mlsanity.com/paper/2609.01526/) (2026)
- [ShapeBench: A Scalable Benchmark and Diagnostic Suite for Standardized Evaluation in Aerodynamic Shape Optimization](https://mlsanity.com/paper/2605.20763/) (2026)
- [My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agents](https://mlsanity.com/paper/2606.11256/) (2026)
- [Adaptive Graph-of-Islands Evolution for Automatic Feature Engineering with LLMs](https://mlsanity.com/paper/2607.23286/) (2026)
- [TRACE: Transition-Aware Residual Control for Multi-Objective Materials Discovery](https://mlsanity.com/paper/2608.23631/) (2026)
- [Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop Discovery](https://mlsanity.com/paper/2609.07655/) (2026)
- [From Hand-Crafted to LLM-Based Variation Operators in Metaheuristics: A Tutorial](https://mlsanity.com/paper/2609.31649/) (2026)

## 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/