Cover Image

DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Yuanhao, Song, Juntong, Zhang, Hanning, Zhang, Tong, Niu, Cheng
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation
by: Zhang, Hanning, et al.
Published: (2025)

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
by: Wu, Zhenyu, et al.
Published: (2024)

RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models
by: Niu, Cheng, et al.
Published: (2023)

VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning
by: Niu, Cheng, et al.
Published: (2024)

Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation
by: Niu, Cheng, et al.
Published: (2024)

Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning
by: Wu, Fei, et al.
Published: (2026)

Reward-SQL: Boosting Text-to-SQL via Stepwise Reasoning and Process-Supervised Rewards
by: Zhang, Yuxin, et al.
Published: (2025)

SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generation
by: Zhang, Xin, et al.
Published: (2026)

Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning
by: Lu, Zimu, et al.
Published: (2024)

Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards
by: Yun, Jaehoon, et al.
Published: (2025)

GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning
by: Zhang, Jianghangfan, et al.
Published: (2025)

The Lessons of Developing Process Reward Models in Mathematical Reasoning
by: Zhang, Zhenru, et al.
Published: (2025)

StepWiser: Stepwise Generative Judges for Wiser Reasoning
by: Xiong, Wei, et al.
Published: (2025)

Entropy-Regularized Process Reward Model
by: Zhang, Hanning, et al.
Published: (2024)

A Stepwise-Enhanced Reasoning Framework for Large Language Models Based on External Subgraph Generation
by: Zhang, Xin, et al.
Published: (2025)

Stepwise Self-Consistent Mathematical Reasoning with Large Language Models
by: Zhao, Zilong, et al.
Published: (2024)

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
by: Lyu, Chengqi, et al.
Published: (2025)

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
by: Xu, Huimin, et al.
Published: (2025)

Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement
by: Liu, Chengyuan, et al.
Published: (2025)

Prioritizing the Best: Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer Correctness
by: Jia, Mengzhao, et al.
Published: (2026)

Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
by: Yuan, Youliang, et al.
Published: (2025)

RM-R1: Reward Modeling as Reasoning
by: Chen, Xiusi, et al.
Published: (2025)

Rubric-Guided Process Reward for Stepwise Model Routing
by: Ye, Shenghao, et al.
Published: (2026)

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation
by: Xu, Zhichao, et al.
Published: (2025)

SMRC: Aligning Large Language Models with Student Reasoning for Mathematical Error Correction
by: Zeng, Biaojie, et al.
Published: (2025)

Evaluating Robustness of Reward Models for Mathematical Reasoning
by: Kim, Sunghwan, et al.
Published: (2024)

ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning
by: Xiong, Xuan, et al.
Published: (2026)

An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoning
by: Sun, Wei, et al.
Published: (2025)

Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning
by: Rajaee, Sara, et al.
Published: (2025)

Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
by: Li, Xintong, et al.
Published: (2026)

Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards
by: Hwang, Hyeonbin, et al.
Published: (2024)

Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning
by: Wang, Li, et al.
Published: (2026)

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
by: Huang, Weiyang, et al.
Published: (2026)

Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning
by: Zhao, Jun, et al.
Published: (2024)

Stepwise Informativeness Search for Efficient and Effective LLM Reasoning
by: Wang, Siyuan, et al.
Published: (2025)

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
by: Yao, Jiarui, et al.
Published: (2025)

StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning
by: Wang, Hao, et al.
Published: (2026)

Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
by: Li, Yansi, et al.
Published: (2025)

Triviality Corrected Endogenous Reward
by: Wang, Xinda, et al.
Published: (2026)

THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
by: Chang, Qikai, et al.
Published: (2025)