arXiv:2611.26186v1 Announce Type: cross
Abstract: 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.
Trending
- Six Products And Services Google Discontinued In 2026
- Reward misalignment as an opportunity for materials discovery
- The Features You’re Actually Paying $450 Extra For
- Thermodynamically Consistent Neural Networks for a Universal Fluid Gibbs Free Energy Equation of State
- Why Does Your Phone Say No Service Even With A SIM Card?
- From Sessions to Serving: Integrating LLM-Based Embeddings into Retrieval for Production Content Recommendation
- The Free Raspberry Pi Tool You Should Be Using To Access It Remotely
- Fixed-Budget RLVR Trades Test-Time Scaling for In-Budget Accuracy
