Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists
Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Zhou, Lianhao, Ling, Hongyi, Yan, Keqiang, Zhao, Kaiji, Qian, Xiaoning, Arróyave, Raymundo, Qian, Xiaofeng, Ji, Shuiwang
Institution: Texas A&M University
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: green
Funders: National Science Foundation, U.S. Department of Energy, National Institutes of Health, Office of Science, American Chemical Society Petroleum Research Fund, Advanced Research Projects Agency, Division of Materials Research, Division of Civil, Mechanical and Manufacturing Innovation, Biological and Environmental Research, Army Research Laboratory
Awards: Collaborative Research: Probing quasiparticle excitations in TMDC Moiré superlattices for revealing and understanding novel two-dimensional correlated phases, Collaborative Research: SHF: Medium: Data-Efficient Uncovering of Rare Design Failures for Reliability-Critical Circuits, Strain-Memory Effects on Solid-State Transformation, Collaborative Research: Machine Learning-assisted Ultrafast Physical Vapor Deposition of High Quality, Large-area Functional Thin Films, G1797209618, G2113400439, DMREF: AI-Guided Accelerated Discovery of Multi-Principal Element Multi-Functional Alloys, G4198830050, G5236897429, G5259331294, G5634181180, Collaborative Research: III: Medium: Conditional Transport: Theory, Methods, Computation, and Applications, G8365304635
OpenAlex ID: W4417114649