http://arxiv.org/abs/2508.19229\n
- \n
- Reframes stepwise reward modeling as a reasoning task: outputs CoT + judgment. \n
- Trained by RL using relative outcomes of rollouts.
Results:
(1) SOTA performance on ProcessBench!
(2) Improves policy at train time.
(3) Improves inference-time search. \n
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\nThe following papers were recommended by the Semantic Scholar API
\n- \n
- Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner (2025) \n
- GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning (2025) \n
- RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback (2025) \n
- Posterior-GRPO: Rewarding Reasoning Processes in Code Generation (2025) \n
- Promoting Efficient Reasoning with Verifiable Stepwise Reward (2025) \n
- Libra: Assessing and Improving Reward Model by Learning to Think (2025) \n
- Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models (2025) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Papers
arxiv:2508.19229
StepWiser: Stepwise Generative Judges for Wiser Reasoning
Published on Aug 26, 2025
Abstract
A generative judge model, StepWiser, uses reinforcement learning to provide step-by-step reasoning feedback, improving both training and inference performance of policy models.
AI-generated summary
As models increasingly leverage multi-step reasoning strategies to solve complex problems, supervising the logical validity of these intermediate steps has become a critical research challenge. Process reward models address this by providing step-by-step feedback, but current approaches have two major drawbacks: they typically function as classifiers without providing explanations, and their reliance on supervised fine-tuning with static datasets limits generalization. Inspired by recent advances, we reframe stepwise reward modeling from a classification task to a reasoning task itself. We thus propose a generative judge that reasons about the policy model's reasoning steps (i.e., meta-reasons), outputting thinking tokens before delivering a final verdict. Our model, StepWiser, is trained by reinforcement learning using relative outcomes of rollouts. We show it provides (i) better judgment accuracy on intermediate steps than existing methods; (ii) can be used to improve the policy model at training time; and (iii) improves inference-time search.
Community
🪜Introducing: StepWiser🦉
📝: http://arxiv.org/abs/2508.19229
- Reframes stepwise reward modeling as a reasoning task: outputs CoT + judgment.
- Trained by RL using relative outcomes of rollouts.
Results:
(1) SOTA performance on ProcessBench!
(2) Improves policy at train time.
(3) Improves inference-time search.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner (2025)
- GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning (2025)
- RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback (2025)
- Posterior-GRPO: Rewarding Reasoning Processes in Code Generation (2025)
- Promoting Efficient Reasoning with Verifiable Stepwise Reward (2025)
- Libra: Assessing and Improving Reward Model by Learning to Think (2025)
- Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2508.19229 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2508.19229 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2508.19229 in a Space README.md to link it from this page.