Image de couverture de livre

Unmasking Reasoning Processes: A Process-aware Benchmark for Evaluating Structural Mathematical Reasoning in LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zheng, Xiang, Zhai, Weiqi, Wang, Wei, Yang, Boyu, Li, Wenbo, Luo, Ruixiang, Sun, Haoxiang, Wang, Yucheng, Li, Zhengze, Wang, Meng, Du, Yuetian, Lin, Guojie, Wang, Yaxuan, Xu, Xiaoxiao, Mo, Yanhu, Ren, Xuan, Wei, Hu, Zhao, Bing
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning
par: Wu, Lingyan, et autres
Publié: (2026)

DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
par: Sun, Haoxiang, et autres
Publié: (2026)

SKYLENAGE Technical Report: Mathematical Reasoning and Contest-Innovation Benchmarks for Multi-Level Math Evaluation
par: Wei, Hu, et autres
Publié: (2025)

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation
par: Xu, Huimin, et autres
Publié: (2025)

From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling
par: Chen, Zhengyu, et autres
Publié: (2025)

Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations
par: Li, Chunyang, et autres
Publié: (2025)

Unlocking Multimodal Mathematical Reasoning via Process Reward Model
par: Luo, Ruilin, et autres
Publié: (2025)

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
par: Wang, Xiangfeng, et autres
Publié: (2026)

Discovering Process-Outcome Credit in Multi-Step LLM Reasoning
par: Wang, Xiangwei, et autres
Publié: (2026)

Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning
par: Wang, Zixuan, et autres
Publié: (2026)

ProcessBench: Identifying Process Errors in Mathematical Reasoning
par: Zheng, Chujie, et autres
Publié: (2024)

Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning
par: Zhu, Jiachen, et autres
Publié: (2025)

Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
par: Li, Ang, et autres
Publié: (2025)

Process-of-Thought Reasoning for Videos
par: Zhang, Jusheng, et autres
Publié: (2026)

Rewarding Graph Reasoning Process makes LLMs more Generalized Reasoners
par: Peng, Miao, et autres
Publié: (2025)

Athena: Enhancing Multimodal Reasoning with Data-efficient Process Reward Models
par: Wang, Shuai, et autres
Publié: (2025)

Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs
par: Zhu, Shaojie, et autres
Publié: (2023)

An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems
par: Hao, Yuren, et autres
Publié: (2025)

Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps
par: Cui, Yu, et autres
Publié: (2025)

Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning
par: Li, Zhen, et autres
Publié: (2025)

Multimodal LLMs Can Reason about Aesthetics in Zero-Shot
par: Jiang, Ruixiang, et autres
Publié: (2025)

Examining False Positives under Inference Scaling for Mathematical Reasoning
par: Wang, Yu, et autres
Publié: (2025)

FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
par: Wang, Zeyu, et autres
Publié: (2026)

MathScale: Scaling Instruction Tuning for Mathematical Reasoning
par: Tang, Zhengyang, et autres
Publié: (2024)

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
par: Chegini, Atoosa, et autres
Publié: (2026)

BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs
par: Wang, Ben, et autres
Publié: (2026)

Enhancing Numerical Reasoning with the Guidance of Reliable Reasoning Processes
par: Wang, Dingzirui, et autres
Publié: (2024)

Improve Mathematical Reasoning in Language Models by Automated Process Supervision
par: Luo, Liangchen, et autres
Publié: (2024)

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
par: Yu, Zhuohao, et autres
Publié: (2024)

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
par: Liang, Jianxin, et autres
Publié: (2025)

MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset
par: Wang, Weiqi, et autres
Publié: (2024)

From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs
par: Wang, Shaojie, et autres
Publié: (2026)

Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization
par: Zhai, Zhiyuan, et autres
Publié: (2026)

An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoning
par: Sun, Wei, et autres
Publié: (2025)

Making Mathematical Reasoning Adaptive
par: Lai, Zhejian, et autres
Publié: (2025)

Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning
par: Yang, Zhaohui, et autres
Publié: (2025)

Coarse-to-Fine Process Reward Modeling for Mathematical Reasoning
par: Hu, Yulan, et autres
Publié: (2025)

The Lessons of Developing Process Reward Models in Mathematical Reasoning
par: Zhang, Zhenru, et autres
Publié: (2025)

STAR : Bridging Statistical and Agentic Reasoning for Large Model Performance Prediction
par: Wang, Xiaoxiao, et autres
Publié: (2026)

Verifiable Process Rewards for Agentic Reasoning
par: Yuan, Huining, et autres
Publié: (2026)