GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916039224197120 |
|---|---|
| author | Soleymanibrojeni, Mohammad Aydin, Roland Guedes-Sobrinho, Diego Dias, Alexandre C. Piotrowski, Maurício J. Wenzel, Wolfgang Rêgo, Celso Ricardo Caldeira |
| author_facet | Soleymanibrojeni, Mohammad Aydin, Roland Guedes-Sobrinho, Diego Dias, Alexandre C. Piotrowski, Maurício J. Wenzel, Wolfgang Rêgo, Celso Ricardo Caldeira |
| contents | Predictive atomistic simulations have propelled materials discovery, yet routine setup and debugging still demand computer specialists. This know-how gap limits Integrated Computational Materials Engineering (ICME), where state-of-the-art codes exist but remain cumbersome for non-experts. We address this bottleneck with GENIUS, an AI-agentic workflow that fuses a smart Quantum ESPRESSO knowledge graph with a tiered hierarchy of large language models supervised by a finite-state error-recovery machine. Here we show that GENIUS translates free-form human-generated prompts into validated input files that run to completion on $\approx$80% of 295 diverse benchmarks, where 76% are autonomously repaired, with success decaying exponentially to a 7% baseline. Compared with LLM-only baselines, GENIUS halves inference costs and virtually eliminates hallucinations. The framework democratizes electronic-structure DFT simulations by intelligently automating protocol generation, validation, and repair, opening large-scale screening and accelerating ICME design loops across academia and industry worldwide. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06404 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols Soleymanibrojeni, Mohammad Aydin, Roland Guedes-Sobrinho, Diego Dias, Alexandre C. Piotrowski, Maurício J. Wenzel, Wolfgang Rêgo, Celso Ricardo Caldeira Artificial Intelligence Materials Science Chemical Physics Predictive atomistic simulations have propelled materials discovery, yet routine setup and debugging still demand computer specialists. This know-how gap limits Integrated Computational Materials Engineering (ICME), where state-of-the-art codes exist but remain cumbersome for non-experts. We address this bottleneck with GENIUS, an AI-agentic workflow that fuses a smart Quantum ESPRESSO knowledge graph with a tiered hierarchy of large language models supervised by a finite-state error-recovery machine. Here we show that GENIUS translates free-form human-generated prompts into validated input files that run to completion on $\approx$80% of 295 diverse benchmarks, where 76% are autonomously repaired, with success decaying exponentially to a 7% baseline. Compared with LLM-only baselines, GENIUS halves inference costs and virtually eliminates hallucinations. The framework democratizes electronic-structure DFT simulations by intelligently automating protocol generation, validation, and repair, opening large-scale screening and accelerating ICME design loops across academia and industry worldwide. |
| title | GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols |
| topic | Artificial Intelligence Materials Science Chemical Physics |
| url | https://arxiv.org/abs/2512.06404 |