Skip to content
Research

Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation.

arXiv:2608.28886v2 Announce Type: replace-cross Abstract: What does a generation loop gain from learning on its own verified successes? In cycles of generate, verify, select and LoRA-consolidate on online bin packing, training on value-filtered candidates shif

arXiv cs.AIResearch source·