AI RESEARCH
Fibration Policy Optimization
arXiv CS.LG
•
ArXi:2603.08239v1 Announce Type: new Large language models are increasingly trained as heterogeneous systems spanning multiple domains, expert partitions, and agentic pipelines, yet prevalent proximal objectives operate at a single scale and lack a principled mechanism for coupling token-level, trajectory-level, and higher-level hierarchical stability control.