Li squared SAO: Lifting Light Singl-Rollout Asynchronous RL Optimization via Group-Relative Actor-Critic Bootstrapping

arXiv:2610.40726 · cs.CL, cs.LG · Submitted 2026-10-29 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-10-29

Updated: 2026-10-29

Terminology

Related papers