cs.AI, cs.CL, cs.LG

Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignment

arXiv:2604.25136v1 Announce Type: new
Abstract: We propose Frictive Policy Optimization (FPO), a framework for learning language model policies that regulate not only what to say, but when and how to intervene in order to manage epistemic and normativ…