arXiv cs.AI· Dingyang Lyu, Jing Gao, Zhonghao Chang, Jingjie Huang, Xiangran Cheng, Xin He, Yongda Huang, Zefeng Li, Jiahui Liu, Jian Wen, Feng Yu, Bonan Zhu, Yongheng Li, Hongwei Du, Baole Wei, Ziheng Lu·· 12 小时前AI 评分51
MatOS：面向材料研究的智能体操作系统
MatOS: An Agent Operating System for Materials Research
AI 导读
MatOS 是一个面向材料研究的智能体操作系统，由分层科学资产图、带科学检查的有状态自适应工作流和证据驱动的资产演化三部分组成。在 ResearchClawBench 上，它用相同基座模型比此前最佳智能体提升 11.15%，并在 MatTools 和 SciAgentGym 上分别超过 Codex CLI 2.13% 和 4.17%。
正文
Authors:Dingyang Lyu, Jing Gao, Zhonghao Chang, Jingjie Huang, Xiangran Cheng, Xin He, Yongda Huang, Zefeng Li, Jiahui Liu, Jian Wen, Feng Yu, Bonan Zhu, Yongheng Li, Hongwei Du, Baole Wei, Ziheng Lu
Abstract:Materials research relies on scattered and growing data, knowledge, and simulation tools, and a single study often spans multi-day workflows across literature analysis, computation, and experiment. Large language model agents can now retrieve materials data, operate simulation codes, and close design-synthesis-characterization loops with autonomous laboratories. However, extending these agents with new capabilities, keeping long-running tasks on track, and letting them learn from past tasks and user feedback remain difficult. Here we present MatOS, an agent operating system for materials research with three core components: (1) a layered scientific asset graph that organizes data, knowledge, tools, skills, roles, and workflows as reusable assets; (2) a stateful adaptive workflow that runs tasks as explicit execution graphs with scientific checks, so that they can be resumed and traced; and (3) evidence-driven asset evolution, which revises these assets from execution records and user feedback. On ResearchClawBench, MatOS improves on the previously best-performing agent by 11.15% with the same base model and extends the cost-score Pareto frontier. With a common base model, it outperforms Codex CLI and Claude Code, exceeding Codex CLI by 2.13% on MatTools and 4.17% on SciAgentGym. In eight research cases, MatOS narrowed more than 30 million candidate structures to 97 solid-electrolyte candidates, identified 89 halide variants with higher computed conductivity than their parent structures, linked the force errors of 11 pretrained interatomic potentials to local atomic environments, and supported two new methods that reduce errors by 3.1% and 13.6% relative to their baselines. These results show that organizing research capabilities as reusable, evolving assets enables agents to carry out long, multistage materials studies. Code is available at this https URL.
| Comments: | 54 pages, 21 figures, 11 tables |
| Subjects: | Artificial Intelligence (cs.AI); Materials Science (cond-mat.mtrl-sci) |
| Cite as: | arXiv:2610.34203 [cs.AI] |
| (or arXiv:2610.34203v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34203 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dingyang Lyu [view email]
[v1]
Sun, 25 Oct 2026 10:44:16 UTC (14,868 KB)
来源：arXiv cs.AI · arxiv.org