跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26186 · v1

Reward misalignment as an opportunity for materials discovery

首次提交 2026-11-19 22:36
版本更新 2026-11-19 22:36
雷达观测 2026-11-20 16:53
arXiv ↗PDF ↗

摘要

Reward misalignment is usually regarded as a failure of artificial intelligence. In materials discovery with generative AI models, however, disagreement between predefined rewards and expert judgment may reveal materials that the rewards overlook. We investigate this possibility using electronic flat bands as a prime example. Experts mostly agree with a numerical bandwidth score, but their disagreements are systematic and cannot be explained by an estimated 5% rate of mistaken labels. We learn the experts' preferences from pairwise comparisons and use them to guide a crystal diffusion model. The learned preferences and numerical score agree on the flattest bands but diverge elsewhere. For example, the preferences favor KCo2As2 and CoGa, reported compounds with partially flat bands that the score would discard. The framework also extends to synthesizability and phonon properties. Our findings suggest that reward misalignment can expose opportunities for materials discovery beyond what fixed rewards are designed to find.

作者备注:33 pages (15 pages main text and 18 pages Supplementary Information), 4 figures

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 22:36 · 最新观测版本

Reward misalignment as an opportunity for materials discovery

Reward misalignment is usually regarded as a failure of artificial intelligence. In materials discovery with generative AI models, however, disagreement between predefined rewards and expert judgment may reveal materials that the rewards overlook. We investigate this possibility using electronic flat bands as a prime example. Experts mostly agree with a numerical bandwidth score, but their disagreements are systematic and cannot be explained by an estimated 5% rate of mistaken labels. We learn the experts' preferences from pairwise comparisons and use them to guide a crystal diffusion model. The learned preferences and numerical score agree on the flattest bands but diverge elsewhere. For example, the preferences favor KCo2As2 and CoGa, reported compounds with partially flat bands that the score would discard. The framework also extends to synthesizability and phonon properties. Our findings suggest that reward misalignment can expose opportunities for materials discovery beyond what fixed rewards are designed to find.

查看此版本解读 →查看此版本原文 ↗