# MLIPilot: LLM-Driven Auto-Research for Machine-Learned Interatomic Potentials

arXiv: https://arxiv.org/abs/2605.30889 · HTML: https://mlsanity.com/paper/2605.30889/

## Key facts

- Cited by 3 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 18 of its 37 references that are in the map.
- First posted on arXiv 29 May 2026.

## 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, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials](https://mlsanity.com/paper/2101.03164/) (2021)
- [MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields](https://mlsanity.com/paper/2206.07697/) (2022)
- [BOHB: Robust and Efficient Hyperparameter Optimization at Scale](https://mlsanity.com/paper/1807.01774/) (2018)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [GemNet: Universal Directional Graph Neural Networks for Molecules](https://mlsanity.com/paper/2106.08903/) (2021)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics](https://mlsanity.com/paper/2204.05249/) (2022)
- [Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules](https://mlsanity.com/paper/2011.14115/) (2020)
- [Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations](https://mlsanity.com/paper/2210.07237/) (2022)
- [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)

## Built on by (most cited first, 3 of 3)

- [Science Done on a Machine by a Machine: AI Agents in Computational Chemistry](https://mlsanity.com/paper/2608.18508/) (2026)
- [The convergent laboratory: when AI reasoning, autonomous experiments, high performance and quantum computing reshape chemistry](https://mlsanity.com/paper/2609.05643/) (2026)
- [MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials](https://mlsanity.com/paper/2609.08399/) (2026)

## Abstract (arXiv)

Constructing production-quality machine-learned interatomic potentials (MLIPs) requires balancing accuracy, dynamical stability, and computational throughput under constraints that are not captured by a single training loss. We introduce MLIPilot, an auto-research framework in which tool-calling large language models propose hypotheses, edit MLIP training code, launch HPC jobs, and accept or revert changes using a fixed, physically constrained scorecard. We evaluate MLIPilot on MACE potential optimization using both commercial and open-weight LLM agents, including GPT-5.5, GPT-4.1, Mistral-24B, and Qwen3-32B. The benchmarks span molecular and periodic settings: a QM7-derived dataset for which we generated B3LYP/6-31G(d) energies and forces, and a Cu EMT dataset with periodic copper supercells labeled by ASE's Effective Medium Theory calculator. Across these benchmarks, the strongest agents move initially constraint-violating baselines to accepted models by discovering useful training strategies, including output normalization, loss-function changes, progressive training schedules, and model-capacity adjustments. These results suggest that LLM agents can serve as autonomous operators for scientific machine-learning workflows when their search is constrained by domain-specific validation criteria, shifting part of MLIP development from manual trial-and-error toward auditable, automated experimentation.