Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows

TL;DR

Lang2MLIP leverages large language models within a multi-agent framework to automate and adapt the development of machine learning interatomic potentials from natural language instructions, reducing reliance on expert knowledge.

Contribution

This work introduces a novel multi-agent system that formulates MLIP development as a decision-making process guided by LLMs, enabling end-to-end automation without fixed pipelines.

Findings

Successfully applied to a complex solid electrolyte interphase system

Demonstrates adaptability and self-correction in MLIP development

Shows potential for making MLIP creation accessible to non-experts

Abstract

Developing machine learning interatomic potentials (MLIPs) for complex materials systems remains challenging because it requires expertise in atomistic simulations, machine learning, and workflow design, as well as iterative active learning procedures. Existing automated pipelines typically assume a fixed sequence of stages or depend on domain experts, which limits their adaptability to heterogeneous materials systems where the optimal curriculum is not known in advance. To lower the barrier to developing MLIPs for non-experts, we propose Lang2MLIP, a multi-agent framework that takes natural-language input and formulates end-to-end MLIP development as a sequential decision-making problem solved by large language models (LLMs). At each step, a decision-making agent observes the current dataset, model, evaluation results, and execution log, and then automatically selects an appropriate action to improve the model. This removes the need for a predefined pipeline and enables the agent to self-correct by revisiting earlier subsystems when new failures arise. We evaluate this approach on a solid electrolyte interphase (SEI) system with multiple components and interfaces. These results suggest that LLM-based multi-agent systems are a promising direction for automating MLIP development and making it more accessible to non-experts.