Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement By Wenbo Huang, Jianxin Bi, Shunyu Yang, Ruiyang Si, Rui Ni · ArXiv · AI/CL/LG · Nov 5, 2026 ArXiv · AI/CL/LG's note score 4 Categories: Research