LLM-Driven Discovery of High-Entropy Catalysts via Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2603.15712v1
• Date: Mon, 16 Mar 2026 14:10:52 GMT
• Title: LLM-Driven Discovery of High-Entropy Catalysts via Retrieval-Augmented Generation
• Abstract summary: This paper demonstrates how large language models can assist the catalyst discovery process.<n>We introduce a retrieval-augmented generation framework that enables GPT-4 to navigate chemical space.<n>Our approach generated over 250 catalyst candidates with an 82% thermodynamic stability rate.
• Score: 2.2716047672389306
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: CO2 reduction requires efficient catalysts, yet materials discovery remains bottlenecked by 10-20 year development cycles requiring deep domain expertise. This paper demonstrates how large language models can assist the catalyst discovery process by helping researchers explore chemical spaces and interpret results when augmented with retrieval-based grounding. We introduce a retrieval-augmented generation framework that enables GPT-4 to navigate chemical space by accessing a database of 50,000+ known materials, adapting general-purpose language understanding for high-throughput materials design. Our approach generated over 250 catalyst candidates with an 82% thermodynamic stability rate while addressing multi-objective constraints: 68% achieved <$100/kg cost with metallic conductivity (band gap<0.1eV) and mechanical stability (B/G>1.75). The best-performing Fe0.2Co0.2Ni0.2Ir0.1Ru0.3 achieves 0.285V limiting potential (25% improvement over IrO2), while Cr0.2Fe0.2Co0.3Ni0.2Mo0.1 optimally balances performance-cost trade-offs at $18/kg. Volcano plot analysis confirms that 78% of LLM-generated catalysts cluster near the theoretical activity optimum, while our system achieves 200x computational efficiency compared to traditional high-throughput screening. By demonstrating that retrieval-augmented generation can ground AI creativity in physical constraints without sacrificing exploration, this work demonstrates an approach where natural language interfaces can streamline materials discovery workflows, enabling researchers to explore chemical spaces more efficiently while the LLM assists in result interpretation and hypothesis generation.

Related papers

• Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin [1.2947828742859666]
  CatDT (Catalysis Digital Twin) is a self-evolving multi-agent system that builds an autonomous digital twin of a working catalyst.<n>Eight specialized agents and 27 scientific tools predict stable facets, reconstruct working surfaces, enumerate and rank reaction pathways, locate transition states, and compute kinetics in 5-30 min on a single GPU.
  arXiv  Detail & Related papers  (2026-06-03T16:10:58Z)
• ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding [56.94419746470799]
  Large Language Models (LLMs) have revolutionized scientific text processing, but exhibit a significant capability gap when interpreting chemical reaction diagrams.<n>We propose the Chemical Visual Activation (ChemVA) framework, which employs a Visual Anchor mechanism to ground functional groups.<n>We evaluate our approach on OCRD-Bench, a newly constructed dataset featuring dense visual-semantic contexts.
  arXiv  Detail & Related papers  (2026-05-17T01:12:50Z)
• Catalyst-Agent: Autonomous heterogeneous catalyst screening and optimization with an LLM Agent [10.596902977676807]
  We introduce Catalyst-Agent, a server-based, LLM-powered AI agent.<n>It can explore vast material databases using the OPTIMADE API.<n> Catalyst-Agent achieves a success rate of 23-34 percent among all the materials it chooses and evaluates.
  arXiv  Detail & Related papers  (2026-03-01T22:44:56Z)
• From Memorization to Creativity: LLM as a Designer of Novel Neural-Architectures [48.83701310501069]
  Large language models (LLMs) excel in program synthesis, yet their ability to autonomously navigate neural architecture design-balancing reliability, performance, and structural novelty--remains underexplored.<n>We address this by placing a code-oriented LLM within a closed-loop synthesis framework, analyzing its evolution over 22 supervised fine-tuning cycles.
  arXiv  Detail & Related papers  (2026-01-06T13:20:28Z)
• Adaptive Physics-Informed Neural Networks with Multi-Category Feature Engineering for Hydrogen Sorption Prediction in Clays, Shales, and Coals [1.5749416770494706]
  This study introduces an adaptive physics-informed neural network (PINN) framework to enhance hydrogen sorption prediction.<n>The PINN employs deep residual networks with multi-head attention, optimized via adaptive loss functions and Monte Carlo dropout for uncertainty quantification.<n>The framework demonstrates robust lithology-specific performance across clay minerals, shales, and coals, maintaining 85-91% reliability scores.
  arXiv  Detail & Related papers  (2025-08-24T19:41:33Z)
• Inorganic Catalyst Efficiency Prediction Based on EAPCR Model: A Deep Learning Solution for Multi-Source Heterogeneous Data [9.022023762759641]
  This study introduces the Embedding-Attention-Permutated CNN-Residual (EAPCR) deep learning model.<n>EAPCR constructs a feature association matrix using embedding and attention mechanisms and enhances predictive performance.<n>We evaluate EAPCR on datasets from heterogeneous photocatalysis, thermal, and electrocatalysis.
  arXiv  Detail & Related papers  (2025-03-10T15:10:22Z)
• Machine Learning for Methane Detection and Quantification from Space -- A survey [49.7996292123687]
  Methane (CH_4) is a potent anthropogenic greenhouse gas, contributing 86 times more to global warming than Carbon Dioxide (CO_2) over 20 years. This work expands existing information on operational methane point source detection sensors in the Short-Wave Infrared (SWIR) bands. It reviews the state-of-the-art for traditional as well as Machine Learning (ML) approaches.
  arXiv  Detail & Related papers  (2024-08-27T15:03:20Z)
• xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics [69.14652127492438]
  State-of-the-art machine translation evaluation metrics like xCOMET achieve high correlation with human judgment but rely on large encoders. We employ distillation, quantization, and pruning techniques to create efficient xCOMET alternatives. Our experiments show that, using quantization, xCOMET can be compressed up to three times with no quality degradation.
  arXiv  Detail & Related papers  (2024-06-20T17:58:34Z)
• Adaptive Catalyst Discovery Using Multicriteria Bayesian Optimization with Representation Learning [17.00084254889438]
  High-performance catalysts are crucial for sustainable energy conversion and human health. The discovery of catalysts faces challenges due to the absence of efficient approaches to navigating vast and high-dimensional structure and composition spaces.
  arXiv  Detail & Related papers  (2024-04-18T18:11:06Z)
• Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation [58.550710456745726]
  Fine-tuning is the most effective way of adapting pre-trained large language models (LLMs) to downstream applications. Existing techniques on efficient fine-tuning can only achieve limited reduction of such FLOPs. We present GreenTrainer, a new technique that adaptively evaluates different tensors' backpropagation costs and contributions to the fine-tuned model accuracy.
  arXiv  Detail & Related papers  (2023-09-22T21:55:18Z)
• PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design [102.9593507372373]
  Catalyst materials play a crucial role in the electrochemical reactions involved in industrial processes. Machine learning holds the potential to efficiently model materials properties from large amounts of data. We propose task-specific innovations applicable to most architectures, enhancing both computational efficiency and accuracy.
  arXiv  Detail & Related papers  (2022-11-22T05:24:30Z)
• The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysis [9.9765107020148]
  General machine learning potential that spans the chemical space of oxide materials is still out of reach. Open Catalyst 2022(OC22) dataset consists of 62,521 Density Functional Theory (DFT) relaxations across a range of oxide materials. We study whether combining datasets leads to better results, even if they contain different materials or adsorbates.
  arXiv  Detail & Related papers  (2022-06-17T17:54:10Z)
• Unassisted Noise Reduction of Chemical Reaction Data Sets [59.127921057012564]
  We propose a machine learning-based, unassisted approach to remove chemically wrong entries from data sets. Our results show an improved prediction quality for models trained on the cleaned and balanced data sets.
  arXiv  Detail & Related papers  (2021-02-02T09:34:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.