语言模型中的对齐算法的机制分析
09850v1 Announce Type: new Abstract: Post-training alignment algorithms are predominantly evaluated as black boxes, obsc
共找到 3320 篇相关文章
09850v1 Announce Type: new Abstract: Post-training alignment algorithms are predominantly evaluated as black boxes, obsc
arXiv:2606.10094v1 Announce Type: new Abstract: Classical theories of cognition describe problem solving as exploratory
10086v1 Announce Type: new Abstract: This paper develops a theory of exploratory adaptation under AI-assisted optimizati
arXiv:2606.10062v1 Announce Type: new Abstract: Foundation-model agents are increasingly long-lived systems that remembe