SLDBench v2: Active Scaling Law Discovery
SLDBench v2 is introduced with two extensions, and active scaling law discovery is introduced: an agent chooses which experiments to run, pays each one's recorded cost, and revises its law as outcomes arrive, and is scored on the same hidden extrapolation targets as in the passive setting.
Ling-Bei Meng, Rui Huang, Zhi-Rong Shen et al.
· 0 citations