arXiv:2605.17291v2 cs.LG

Step-wise Rubric Rewards for LLM Reasoning

Weichu Xie, Haozhe Zhao, Wenpu Liu, Yongfu Zhu, Liang Chen, Minghao Ye, Zirong Chen, Yuqi Xu, Shuai Dong, Ziyue Wang, Xinbo Xu, Kean Shi, Ruoyu Wu, Xiaoying Zhang, Wenqi Shao 외 3명

제출 2026-11-02

원문 초록

Reinforcement Learning with Verifiable Rewards (RLVR) improves language-model reasoning using final-answer correctness, but lacks supervision for intermediate steps. Rubric-based methods such as Rubrics as Rewards (RaR) provide finer-grained criteria, yet collapse rubric scores into a response-level scalar. This loses criterion-level structure, rewards flawed steps in correct responses, penalizes valid steps in incorrect responses, and can encourage unbounded self-correction. In 1,000 sampled problems, 18.2% of steps in answer-correct responses are wrong, while 49.9% of steps in answer-incorrect responses are correct. We propose Step-wise Rubrics as Rewards (SRaR), which (i) uses an LLM judge to assign rubric items to reasoning steps, (ii) normalizes step scores across rollouts to focus learning on quality differences, and (iii) combines step-wise and outcome rewards through a decoupled advantage estimator that preserves a stable outcome baseline. We also construct a 16K-problem rubric dataset by contrastively distilling criteria from verified correct and flawed reasoning paths. Across six math benchmarks, SRaR improves average accuracy over RaR by 3.57 and 2.75 points on Qwen3-8B-Non-Thinking and Qwen3-32B-Non-Thinking, respectively. On AIME 2025, it increases the Faithful Reasoning Rate from 34.5% to 46.7% and reduces self-correction looping from 48.1% to 26.5%. SRaR also achieves the best results on three of four code-generation benchmarks.

제출 이력

확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.

  1. arXiv:2605.17291v2제출 시각 미확인

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

공통 태그로 연결된 공개 논문이 아직 없습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.