Paper recorded by Signals 4 on 2026-10-26 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-26 on arXiv · recorded by Signals 4 on 2026-10-27
Category: cs.AI · 人工智能 · first seen 2026-10-27
Reinforcement learning with verifiable rewards trains on cheap checks, such as unit tests, that a policy can learn to game, while a stronger check is too expensive to run on every rollout. We study how to spend a limited strong-verifier budget in GRPO, separating which weakly passing rollouts to audit from what reward a caught hack receives. At a fixed policy state with centered advantages, the ex