Autonomous in-silico inorganic materials discovery via multi-agent physics-aware scientific reasoning
- 1Laboratory for Atomistic and Molecular Mechanics (LAMM), Massachusetts Institute of Technology, Cambridge, MA, USA
- 2Laboratory for Atomistic and Molecular Mechanics (LAMM), Center for Computational Science and Engineering Schwarzman College of Computing Massachusetts Institute of Technology, Cambridge, MA, USA
Abstract
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.
Related
- Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing Experiments
- Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Heterogeneous Catalyst Discovery
- Constructive chemical discovery through autonomous reasoning and experiment
- Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale.
- How the fruit fly connectome can help autonomous materials discovery
BibTeX
@article{ghafarollahi2026autonomous,
title = {{Autonomous in-silico inorganic materials discovery via multi-agent physics-aware scientific reasoning}},
author = {Alireza Ghafarollahi and Markus J. Buehler},
journal = {npj Computational Materials},
year = {2026},
month = jul,
doi = {10.1038/s41524-026-02205-8},
url = {https://doi.org/10.1038/s41524-026-02205-8},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Autonomous in-silico inorganic materials discovery via multi-agent physics-aware scientific reasoning
AU - Alireza Ghafarollahi
AU - Markus J. Buehler
PY - 2026
DA - 2026/07/08
JO - npj Computational Materials
DO - 10.1038/s41524-026-02205-8
UR - https://doi.org/10.1038/s41524-026-02205-8
AB - 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.
SN - 2057-3960
ER -