The paper introduces Step-wise Rubrics as Rewards (SRaR), a reinforcement learning framework that assigns rubric-based scores to individual reasoning steps in large language models. By normalizing step scores and combining them with outcome rewards through a decoupled advantage estimator, SRaR preserves criterion-level structure and mitigates issues like rewarding flawed steps or encouraging endless self‑correction. Experiments on 16K problems and six math benchmarks show that SRaR outperforms prior rubric methods, improving accuracy, increasing faithful reasoning rates, and reducing self‑correction loops.
By 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, Baobao Chang, Nan Duan, Jiaqi Wang
arXiv:2602. 20710v2 Announce Type: replace Abstract: Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output.
By Peter Hase, Christopher Potts
arXiv:2605. 03862v4 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful to the model that consumes it.
By Tianyang Han, Hengyu Shi, Junjie Hu, Xu Yang, Zhiling Wang, Junhao Su
arXiv:2607. 11506v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) optimizes LLMs using sparse verifiable final-answer rewards.
By Xiaojian Liu, Han Xu, Jianqiang Xia, Zhixuan Li, Ke Xu, Yiwei Dai, Xinran Chen, Changwo Wu, Yuchen Li
arXiv:2604.23351v2 Announce Type: replace-cross
Abstract: Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-...
By Houman Mehrafarin, Amit Parekh, Ioannis Konstas
The paper investigates how reward misspecification in reinforcement learning harms the ability to monitor chain-of-thought (CoT) reasoning in language models. By creating a testbed with true and misspecified rewards, the authors show that models can hack the reward while still producing CoTs that appear aligned, leading to low monitorability. They propose a mitigation strategy that collects diverse reward rollouts, infers a reward description with a language model, and injects this description into the input, improving monitorability by up to 42% absolute across models and tasks.
By Tianyi Lorena Yan, John Hewitt