Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards 事件

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards arXiv:2510.01167v2 Announce Type: replace-cross Abstract: Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single objective. We seek to answer what it would take to simultaneously align a model across various domains spanning those with: verifiable rewards, non-verifiable subjective preferences, and complex interactive sc