Paper recorded by Signals 4 on 2026-10-30 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-30 on arXiv · recorded by Signals 4 on 2026-11-02
Category: cs.AI · 人工智能 · first seen 2026-11-02
Reinforcement learning with verifiable rewards (RLVR) has become the standard method for training language models to reason. However, RLVR typically relies solely on outcome correctness, which does not guarantee that the CoT causally contributes to the final answer. Without this connection, outcome rewards may fail to reinforce high-quality reasoning. Existing causality metrics assess CoT causalit