Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| 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 |