Autonomous in-silico inorganic materials discovery via multi-agent physics-aware scientific reasoning
Автономное компьютерное открытие неорганических материалов посредством мультиагентного физически информированного научного рассуждения
2026-07-08
SCID: 54.1/fpdcpbcq
Discuss with AI
DFT calculationsinorganic materials discoverymaterials designmulti-agent AIphysics-aware reasoning
Figures from the paper
Abstract (AI)
Conventional machine learning approaches accelerate in-silico 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 in-silico 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 oxide 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.
Key Findings
1
Across thermoelectric, semiconductor, and perovskite oxide case studies, SparksMatter generated novel stable inorganic structures tailored to specified user objectives.
2
Against frontier models, SparksMatter achieved consistently higher relevance, novelty, and scientific-rigor scores, with significant novelty gains across multiple real-world design tasks in blinded evaluation.
3
SparksMatter is a multi-agent AI system designed to autonomously execute the full in-silico inorganic materials discovery cycle, from ideation and planning through experimentation and iterative refinement.
4
The results indicate that SparksMatter can produce chemically valid, physically meaningful, and creative inorganic materials hypotheses extending beyond existing materials knowledge.
5
The system generates, evaluates, and self-critiques candidate materials while identifying research gaps and recommending follow-up validation using DFT calculations and experimental synthesis and characterization.
Research Object
in-silico inorganic materials discovery and design, including thermoelectric, semiconductor, and perovskite oxide materials
Research Subject
autonomous multi-agent execution and physics-aware refinement of the full materials discovery cycle to generate novel, stable, chemically valid, and physically meaningful candidate structures
Publication Details
Publication Date
2026-07-08
Journal
Publisher
ISSN
Cited by
24
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai10
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation2013
The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies2015
GPT-4 Technical Report2023
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery2024
Sparks of Artificial General Intelligence: Early experiments with GPT-42023
An autonomous laboratory for the accelerated synthesis of inorganic materials2023
Augmenting large language models with chemistry tools2024
Self-Driving Laboratories for Chemistry and Materials Science2024
Towards end-to-end automation of AI research2026
Risks of AI scientists: prioritizing safeguarding over autonomy2025