Saved in:
Bibliographic Details
Main Authors: Zhou, Lianhao, Ling, Hongyi, Yan, Keqiang, Zhao, Kaiji, Qian, Xiaoning, Arróyave, Raymundo, Qian, Xiaofeng, Ji, Shuiwang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.05616
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912420456300544
author Zhou, Lianhao
Ling, Hongyi
Yan, Keqiang
Zhao, Kaiji
Qian, Xiaoning
Arróyave, Raymundo
Qian, Xiaofeng
Ji, Shuiwang
author_facet Zhou, Lianhao
Ling, Hongyi
Yan, Keqiang
Zhao, Kaiji
Qian, Xiaoning
Arróyave, Raymundo
Qian, Xiaofeng
Ji, Shuiwang
contents We aim at designing language agents with greater autonomy for crystal materials discovery. While most of existing studies restrict the agents to perform specific tasks within predefined workflows, we aim to automate workflow planning given high-level goals and scientist intuition. To this end, we propose Materials Agent unifying Planning, Physics, and Scientists, known as MAPPS. MAPPS consists of a Workflow Planner, a Tool Code Generator, and a Scientific Mediator. The Workflow Planner uses large language models (LLMs) to generate structured and multi-step workflows. The Tool Code Generator synthesizes executable Python code for various tasks, including invoking a force field foundation model that encodes physics. The Scientific Mediator coordinates communications, facilitates scientist feedback, and ensures robustness through error reflection and recovery. By unifying planning, physics, and scientists, MAPPS enables flexible and reliable materials discovery with greater autonomy, achieving a five-fold improvement in stability, uniqueness, and novelty rates compared with prior generative models when evaluated on the MP-20 data. We provide extensive experiments across diverse tasks to show that MAPPS is a promising framework for autonomous materials discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05616
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists
Zhou, Lianhao
Ling, Hongyi
Yan, Keqiang
Zhao, Kaiji
Qian, Xiaoning
Arróyave, Raymundo
Qian, Xiaofeng
Ji, Shuiwang
Artificial Intelligence
Materials Science
Computational Physics
We aim at designing language agents with greater autonomy for crystal materials discovery. While most of existing studies restrict the agents to perform specific tasks within predefined workflows, we aim to automate workflow planning given high-level goals and scientist intuition. To this end, we propose Materials Agent unifying Planning, Physics, and Scientists, known as MAPPS. MAPPS consists of a Workflow Planner, a Tool Code Generator, and a Scientific Mediator. The Workflow Planner uses large language models (LLMs) to generate structured and multi-step workflows. The Tool Code Generator synthesizes executable Python code for various tasks, including invoking a force field foundation model that encodes physics. The Scientific Mediator coordinates communications, facilitates scientist feedback, and ensures robustness through error reflection and recovery. By unifying planning, physics, and scientists, MAPPS enables flexible and reliable materials discovery with greater autonomy, achieving a five-fold improvement in stability, uniqueness, and novelty rates compared with prior generative models when evaluated on the MP-20 data. We provide extensive experiments across diverse tasks to show that MAPPS is a promising framework for autonomous materials discovery.
title Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists
topic Artificial Intelligence
Materials Science
Computational Physics
url https://arxiv.org/abs/2506.05616