Autonomous Inorganic Materials Discovery via Multi-Agent Physics-Aware Scientific Reasoning

• URL: http://arxiv.org/abs/2508.02956v1
• Date: Mon, 04 Aug 2025 23:40:43 GMT
• Title: Autonomous Inorganic Materials Discovery via Multi-Agent Physics-Aware Scientific Reasoning
• Abstract summary: We introduce SparksMatter, a multi-agent AI model for automated inorganic materials design.<n>It generates ideas, designing and executing experimental, continuously evaluating and refining results, and proposing candidate materials.<n>The model's performance is evaluated across case studies in thermoelectrics, semiconductors, and perovskite oxides materials design.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Conventional machine learning approaches accelerate inorganic materials design via accurate property prediction and targeted material generation, yet they operate as single-shot models limited by the latent knowledge baked into their training data. A central challenge lies in creating an intelligent system capable of autonomously executing the full inorganic materials discovery cycle, from ideation and planning to experimentation and iterative refinement. We introduce SparksMatter, a multi-agent AI model for automated inorganic materials design that addresses user queries by generating ideas, designing and executing experimental workflows, continuously evaluating and refining results, and ultimately proposing candidate materials that meet the target objectives. SparksMatter also critiques and improves its own responses, identifies research gaps and limitations, and suggests rigorous follow-up validation steps, including DFT calculations and experimental synthesis and characterization, embedded in a well-structured final report. The model's performance is evaluated across case studies in thermoelectrics, semiconductors, and perovskite oxides materials design. The results demonstrate the capacity of SparksMatter to generate novel stable inorganic structures that target the user's needs. Benchmarking against frontier models reveals that SparksMatter consistently achieves higher scores in relevance, novelty, and scientific rigor, with a significant improvement in novelty across multiple real-world design tasks as assessed by a blinded evaluator. These results demonstrate SparksMatter's unique capacity to generate chemically valid, physically meaningful, and creative inorganic materials hypotheses beyond existing materials knowledge.

Related papers

• Generative and multimodal AI for materials prediction and design: Progress, challenges, and perspectives [38.18261110160569]
  novelty in materials discovery encompasses chemical plausibility, structural distinctiveness, property relevance and experimental realisability.<n>We introduce a materials property hierarchy to clarify deployment constraints and distinguish structural, physical and deployment novelty.<n>This framework motivates an evidence-based view of multimodal materials data spanning chemical composition, microstructure, processing, and testing and characterisation.
  arXiv  Detail & Related papers  (2026-07-22T23:06:35Z)
• Perspective: Towards sustainable exploration of chemical spaces with machine learning [49.29528647472741]
  We argue that sustainable progress will rely on open data and models, reusable datasets, and domain-specific AI systems.<n>We highlight emerging strategies to enhance efficiency, including general-purpose machine learning (ML) models, multi-fidelity approaches, model distillation, and active learning.
  arXiv  Detail & Related papers  (2026-03-31T13:29:20Z)
• PeroMAS: A Multi-agent System of Perovskite Material Discovery [51.859972927223936]
  Perovskite Solar Cells (PSCs) are renowned for their superior optoelectronic performance and cost potential.<n>Existing AI approaches focus predominantly on discrete models, including material design, process optimization, and property prediction.<n>We propose a multi-agent system for perovskite material discovery, named PeroMAS.
  arXiv  Detail & Related papers  (2026-02-10T09:33:06Z)
• FIRE-Bench: Evaluating Agents on the Rediscovery of Scientific Insights [63.32178443510396]
  We introduce FIRE-Bench (Full-cycle Insight Rediscovery Evaluation), a benchmark that evaluates agents through the rediscovery of established findings.<n>Even the strongest agents achieve limited rediscovery success (50 F1), exhibit high variance across runs, and display recurring failure modes in experimental design, execution, and evidence-based reasoning.
  arXiv  Detail & Related papers  (2026-02-02T23:21:13Z)
• Towards Agentic Intelligence for Materials Science [73.4576385477731]
  This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining to goal-conditioned agents interfacing with simulation and experimental platforms.<n>To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science.
  arXiv  Detail & Related papers  (2026-01-29T23:48:43Z)
• Sustainable Materials Discovery in the Era of Artificial Intelligence [3.222363676081407]
  We propose to integrate upstream machine learning (ML) assisted materials discovery with downstream lifecycle assessment into a uniform ML-LCA environment.<n>The framework ML-LCA integrates five components, information extraction for building materials-environment knowledge bases, harmonized databases linking properties to sustainability metrics, multi-scale models bridging atomic properties to lifecycle impacts, ensemble prediction of manufacturing pathways with uncertainty quantification, and uncertainty-aware optimization.
  arXiv  Detail & Related papers  (2026-01-29T10:42:44Z)
• Foundation Models for Discovery and Exploration in Chemical Space [57.97784111110166]
  MIST is a family of molecular foundation models trained on large unlabeled datasets.<n>We demonstrate the ability of these models to solve real-world problems across chemical space.
  arXiv  Detail & Related papers  (2025-10-20T17:56:01Z)
• Generative Artificial Intelligence Extracts Structure-Function Relationships from Plants for New Materials [0.0]
  Large language models (LLMs) have reshaped the research landscape by enabling new approaches to knowledge retrieval and creative ideation.<n>We present a first-of-its-kind framework that integrates generative AI with literature from hitherto-unconnected fields such as plant science, biomimetics, and materials engineering.<n>We focus on humidity-responsive systems such as pollen-based materials and Rhapis excelsa leaves, which exhibit self-actuation and adaptive performance.
  arXiv  Detail & Related papers  (2025-08-08T10:41:03Z)
• Artificial Intelligence and Generative Models for Materials Discovery -- A Review [0.0]
  Review aims to discuss different principles of AI-driven generative models that are applicable for materials discovery.<n>We will also highlight specific applications of generative models in designing new catalysts, semiconductors, polymers, or crystals.
  arXiv  Detail & Related papers  (2025-08-05T09:56:27Z)
• Perovskite-R1: A Domain-Specialized LLM for Intelligent Discovery of Precursor Additives and Experimental Design [5.378023608941598]
  Perovskite solar cells (PSCs) have rapidly emerged as a leading contender in next-generation photovoltaic technologies.<n> challenges such as long-term stability, environmental sustainability, and scalable manufacturing continue to hinder their commercialization.<n>Precursor additive engineering has shown promise in addressing these issues by enhancing both the performance and durability of PSCs.<n>We introduce Perovskite-R1, a specialized large language model (LLM) with advanced reasoning capabilities tailored for the discovery and design of PSC precursor additives.
  arXiv  Detail & Related papers  (2025-07-22T07:48:32Z)
• ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data [53.78763789036172]
  We present ChemActor, a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences.<n>This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input.<n>Experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor achieves state-of-the-art performance, outperforming the baseline model by 10%.
  arXiv  Detail & Related papers  (2025-06-30T05:11:19Z)
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization [80.82828320306464]
  Photonic device development (PDD) has achieved remarkable success in designing and implementing new devices for controlling light across various wavelengths, scales, and applications.<n>PDD is an iterative, five-step process that consists of: i.e. deriving device behavior from design parameters, ii. simulating device performance, iv. fabricating the optimal device, and v. measuring device performance.<n>PDD suffers from large optimization landscapes, uncertainties in structural or optical characterization, and difficulties in implementing robust fabrication processes.<n>In this review, we present a comprehensive perspective on these methods to enable machine-learning-assisted PDD
  arXiv  Detail & Related papers  (2025-06-24T23:32:54Z)
• Insights Informed Generative AI for Design: Incorporating Real-world Data for Text-to-Image Output [51.88841610098437]
  We propose a novel pipeline that integrates DALL-E 3 with a materials dataset to enrich AI-generated designs with sustainability metrics and material usage insights.<n>We evaluate the system through three user tests: (1) no mention of sustainability to the user prior to the prompting process with generative AI, (2) sustainability goals communicated to the user before prompting, and (3) sustainability goals communicated along with quantitative CO2e data included in the generative AI outputs.
  arXiv  Detail & Related papers  (2025-06-17T22:33:11Z)
• Towards Fully-Automated Materials Discovery via Large-Scale Synthesis Dataset and Expert-Level LLM-as-a-Judge [6.500470477634259]
  Our work aims to support the materials science community by providing a practical, data-driven resource.<n>We have curated a comprehensive dataset of 17K expert-verified synthesis recipes from open-access literature.<n>AlchemicalBench offers an end-to-end framework that supports research in large language models applied to synthesis prediction.
  arXiv  Detail & Related papers  (2025-02-23T06:16:23Z)
• AIMS-EREA -- A framework for AI-accelerated Innovation of Materials for Sustainability -- for Environmental Remediation and Energy Applications [0.0]
  AIMS-EREA is our novel framework to blend best of breed of Material Science theory with power of Generative AI. This also helps to eliminate the possibility of production of hazardous residues and bye-products of the reactions.
  arXiv  Detail & Related papers  (2023-11-18T12:35:45Z)
• A Comparative Study of Machine Learning Algorithms for Anomaly Detection in Industrial Environments: Performance and Environmental Impact [62.997667081978825]
  This study seeks to address the demands of high-performance machine learning models with environmental sustainability. Traditional machine learning algorithms, such as Decision Trees and Random Forests, demonstrate robust efficiency and performance. However, superior outcomes were obtained with optimised configurations, albeit with a commensurate increase in resource consumption.
  arXiv  Detail & Related papers  (2023-07-01T15:18:00Z)
• ChemVise: Maximizing Out-of-Distribution Chemical Detection with the Novel Application of Zero-Shot Learning [60.02503434201552]
  This research proposes learning approximations of complex exposures from training sets of simple ones. We demonstrate this approach to synthetic sensor responses surprisingly improves the detection of out-of-distribution obscured chemical analytes.
  arXiv  Detail & Related papers  (2023-02-09T20:19:57Z)
• Artificial intelligence approaches for materials-by-design of energetic materials: state-of-the-art, challenges, and future directions [0.0]
  We review advances in AI-driven materials-by-design and their applications to energetic materials. We evaluate methods in the literature in terms of their capacity to learn from a small/limited number of data. We suggest a few promising future research directions for EM materials-by-design, such as meta-learning, active learning, Bayesian learning, and semi-/weakly-supervised learning.
  arXiv  Detail & Related papers  (2022-11-15T14:41:11Z)
• Predictive modeling approaches in laser-based material processing [59.04160452043105]
  This study aims to automate and forecast the effect of laser processing on material structures. The focus is centred on the performance of representative statistical and machine learning algorithms. Results can set the basis for a systematic methodology towards reducing material design, testing and production cost.
  arXiv  Detail & Related papers  (2020-06-13T17:28:52Z)

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.