Imagen de Portada

GRPO and Reflection Reward for Mathematical Reasoning in Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Wang, Zhijie
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning
por: Yang, Zhaohui, et al.
Publicado: (2025)

GRPO is Secretly a Process Reward Model
por: Sullivan, Michael, et al.
Publicado: (2025)

Large Language Models and Mathematical Reasoning Failures
por: Boye, Johan, et al.
Publicado: (2025)

Coarse-to-Fine Process Reward Modeling for Mathematical Reasoning
por: Hu, Yulan, et al.
Publicado: (2025)

Mathematical Computation and Reasoning Errors by Large Language Models
por: Zhang, Liang, et al.
Publicado: (2025)

A Survey on Large Language Models for Mathematical Reasoning
por: Wang, Peng-Yuan, et al.
Publicado: (2025)

Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning
por: Xiao, Wenyi, et al.
Publicado: (2025)

Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning
por: Zhu, Jiachen, et al.
Publicado: (2025)

Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
por: Xu, Yuanda, et al.
Publicado: (2026)

Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning
por: Lu, Leo, et al.
Publicado: (2025)

A Survey on Mathematical Reasoning and Optimization with Large Language Models
por: Forootani, Ali
Publicado: (2025)

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

M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models
por: Wang, Junjian, et al.
Publicado: (2026)

Teaching Large Reasoning Models Effective Reflection
por: Wang, Hanbin, et al.
Publicado: (2026)

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
por: Dai, Yanqi, et al.
Publicado: (2026)

GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO
por: Dipta, Shubhashis Roy, et al.
Publicado: (2026)

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

Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO
por: Pappone, Francesco, et al.
Publicado: (2025)

Unlocking Multimodal Mathematical Reasoning via Process Reward Model
por: Luo, Ruilin, et al.
Publicado: (2025)

Key-Point-Driven Mathematical Reasoning Distillation of Large Language Model
por: Zhu, Xunyu, et al.
Publicado: (2024)

Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning
por: He, Qianxi, et al.
Publicado: (2025)

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

Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models
por: Liu, Yan, et al.
Publicado: (2026)

ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training
por: Ai, Rui, et al.
Publicado: (2026)

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
por: Huang, Runhui, et al.
Publicado: (2026)

GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
por: Tan, Hongze, et al.
Publicado: (2025)

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

Numerical Sensitivity and Robustness: Exploring the Flaws of Mathematical Reasoning in Large Language Models
por: Sun, Zhishen, et al.
Publicado: (2025)

Revisiting Anthropomorphic Reflection Markers in Large Language Model Reasoning
por: Yu, Yahan, et al.
Publicado: (2026)

Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning
por: Chen, Benteng, et al.
Publicado: (2026)

From Reasoning to Code: GRPO Optimization for Underrepresented Languages
por: Pennino, Federico, et al.
Publicado: (2025)

MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning
por: Chen, Jinhao, et al.
Publicado: (2025)

What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning
por: Ma, Yiran, et al.
Publicado: (2024)

Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
por: Mansouri, Omar El, et al.
Publicado: (2025)

Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models
por: Wang, Teng, et al.
Publicado: (2025)

Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection
por: Liu, MingShan, et al.
Publicado: (2025)

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
por: Zhang, Xiaoying, et al.
Publicado: (2025)

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
por: Mirzadeh, Iman, et al.
Publicado: (2024)

CAMA: Enhancing Mathematical Reasoning in Large Language Models with Causal Knowledge
por: Zan, Lei, et al.
Publicado: (2025)

Systematic Optimization of Open Source Large Language Models for Mathematical Reasoning
por: Pawar, Pranav, et al.
Publicado: (2025)