Paper recorded by Signals 4 on 2026-11-02 in cs.LG. Abstract reproduced from arXiv; link to the original below.
Published 2026-11-02 on arXiv · recorded by Signals 4 on 2026-11-03
Category: cs.LG · 机器学习 · first seen 2026-11-03
Group-based reinforcement learning with verifiable rewards (RLVR) learns only from prompts whose sampled completions disagree: all-pass and all-fail groups produce zero relative advantage and burn generation budget without moving the policy. Adaptive schedulers try to steer rollouts toward informative prompts, yet they rely on per-prompt pass-rate trackers that entangle two quantities evolving at