# GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols

arXiv: https://arxiv.org/abs/2512.06404 · HTML: https://mlsanity.com/paper/2512.06404/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 4 of its 33 references that are in the map.
- First posted on arXiv 6 Dec 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 4 of 4)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Is Cosine-Similarity of Embeddings Really About Similarity?](https://mlsanity.com/paper/2403.05440/) (2024)
- [14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon](https://mlsanity.com/paper/2306.06283/) (2023)
- [The Fundamental Principles of Reproducibility](https://mlsanity.com/paper/2011.10098/) (2020)

## Built on by (most cited first, 4 of 4)

- [El Agente Quntur: A research collaborator agent for quantum chemistry](https://mlsanity.com/paper/2602.04850/) (2026)
- [GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation](https://mlsanity.com/paper/2602.15039/) (2026)
- [Harnessing AtomisticSkills for Agentic Atomistic Research](https://mlsanity.com/paper/2605.24002/) (2026)
- [Science Done on a Machine by a Machine: AI Agents in Computational Chemistry](https://mlsanity.com/paper/2608.18508/) (2026)

## Abstract (arXiv)

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 ≈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.