arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.26703cond-mat.mtrl-scics.AIphysics.comp-ph
收藏

可自我进化的代理用于DFT实验能带不匹配的可解释诊断

Discovering physical mechanisms from experiment-simulation mismatches

School of Materials Science and Engineering, Nanyang Technological University(南洋理工大学材料科学与工程学院)

Yue Li, Penghui Yang, Yushan Xiao, Zhonghan Zhang, Jianguo Huang, Yuhao Lu, Cuntai Guan, Bo An, Bijun Tang, Zheng Liu

AI总结:

本文提出XDFT代理,通过自动诊断DFT计算中能带不匹配问题,利用贝叶斯后验更新假设有效性,有效识别78%的不匹配案例,优于随机基线和静态LLM排序。

摘要:

标准密度泛函理论(DFT)常规上会错误分类相关和结构复杂的化合物的电子基态,预测出金属行为,而实验报告为半导体。每种不匹配都编码了特定的非理想性——磁序、电子关联、替代多形体或缺陷——但提取这些信号仍需手动操作。本文引入XDFT,一个闭环代理,可自动诊断不匹配:从精选目录中提出候选假设,执行相应的原理计算测试,并从每次判决更新全局贝叶斯后验。在验证的124种材料基准上,XDFT解决了90个不匹配中的70个(78%),远超均匀随机基线(19%)和静态LLM排序(20%)。内部后验与基准时间线的实证性能一致,解决的案例坍缩为三类元素分类法,提炼为四条静态规则。每个诊断材料返回修正的协议和机制归因;失败案例被标记为实验重新检查的证据支持目标。

英文摘要:

Scientific discovery often begins where observation and prediction disagree. As computation and machine learning survey chemical space, experiment-simulation mismatches are exposed at scale, while tracing them to physical mechanisms remains expert-led. Here we present eXplainable DFT (XDFT), a self-evolving agent that turns this process into an executable search. XDFT formalizes candidate mechanisms as executable hypotheses, adjudicates their consequences against experiment and distils trajectories into priors for later searches. This couples a solving loop from mismatch to mechanism with a learning loop through which solving changes the solver. Across 112 source-audited cases in which standard calculations predict a metal whereas experiments find a semiconductor, XDFT resolved 105 with evidence-supported mechanisms within a single-GPU envelope. After 60 cases, the resolving mechanism ranked among the first three hypotheses for 80% of held-out cases, up from 7% under the initial expert prior. XDFT also returned evidence-graded mechanisms for seven expert-curated questions about physical mechanisms. These results establish experiment-simulation mismatches as tractable starting points for scientific agents that discover physical mechanisms while learning how to find the next.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑