Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards (2026.acl-long)
Copied to clipboard
Youliang Yuan, Qiuyang Mang, Jingbang Chen, Hong Wan, Xiaoyuan Liu, Junjielong Xu, Jen-tse Huang, Wenxuan Wang, Wenxiang Jiao, Pinjia He
| Challenge: | Existing models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning ability. |
| Approach: | They propose a Rubric Reward Model that rewards the entire reasoning trajectory against problem-specific rubrics. |
| Outcome: | The proposed model outperforms outcome-only supervision on four math benchmarks and boosts Verified Pass@1024 from 26.7% to 62.6% and reduces the incidence of Miracle Steps by 71%. |
Similar Papers
Out of Distribution, Out of Luck: Process Rewards Misguide Reasoning Models (2026.eacl-short)
Copied to clipboard
| Challenge: | 80% of reasoning model outputs respond to formatting artifacts rather than mathematical content. |
| Approach: | They evaluate process reward models that provide step-level feedback during inference . they identify distinct reward prediction patterns that differentiate reasoning from non-reasoning model outputs . |
| Outcome: | The proposed model fails to enhance and sometimes degrade reasoning model performance. |
A Comprehensive Survey of Process Reward Models: Data Generation, Model Construction, and Usage (2026.acl-long)
Copied to clipboard
Congmin Zheng, Jiachen Zhu, Zhuoying Ou, Yuxiang Chen, Kangning Zhang, Rong Shan, Zeyu Zheng, Mengyue Yang, Jianghao Lin, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have advanced reasoning ability, yet conventional alignment remains dominated by outcome reward models that judge only final answers. |
| Approach: | They summarize applications across math, code, text, multimodal reasoning, robotics, and agents . goal is to clarify design spaces, reveal open challenges, and guide future research toward fine-grained, robust reasoning alignment. |
| Outcome: | The proposed model enables finer credit assignment, richer diagnostics, and improved robustness. |
R-PRM: Reasoning-Driven Process Reward Modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing Process Reward Models (PRMs) output evaluation scores directly, limiting both learning efficiency and evaluation accuracy. |
| Approach: | They propose a Reasoning-Driven Process Reward Modeling (R-PRM) which activates inherent reasoning to enhance process-level evaluation. |
| Outcome: | The proposed model outperforms baseline models on ProcessBench and PRMBench by 13.9 and 8.5 F1 scores. |
Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models can be substantially improved using outcome-level verification signals. |
| Approach: | They propose a framework where intermediate reasoning steps are checked by deterministic, rule-based verifiers. |
| Outcome: | The proposed framework achieves 20% higher F1 than state-of-the-art models and 6.5% higher than verifiable outcome rewards, with substantial gains in evidence grounding and logical coherence. |
Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards (2026.acl-long)
Copied to clipboard
| Challenge: | Existing PRM datasets are expensive to construct and limited to the mathematical domain. |
| Approach: | They propose a method to generate a corpus of one million reasoning steps using the Planning Domain Definition Language. |
| Outcome: | The proposed model generates a corpus of approximately one million reasoning steps across various PDDL domains and trains them. |
The Lessons of Developing Process Reward Models in Mathematical Reasoning (2025.findings-acl)
Copied to clipboard
Zhenru Zhang, Chujie Zheng, Yangzhen Wu, Beichen Zhang, Runji Lin, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin
| Challenge: | a recent study shows that process reward models can make mistakes, leading to wrong conclusions. |
| Approach: | They propose a consensus filtering mechanism that integrates MC estimation with LLM-as-a-judge to improve model performance and data efficiency. |
| Outcome: | The proposed model outperforms existing open-source alternatives and provides practical guidelines for future research. |
Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models (2026.findings-acl)
Copied to clipboard
Teng Wang, Jiang Zhangyi, Zhenqi He, Hailei Gong, Shenyang Tong, Wenhan Yang, Zeyu Li, Yanan Zheng, Zifan He, Zewen Ye, Shengjie Ma, Jianping Zhang
| Challenge: | Existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps. |
| Approach: | They propose a reward model approach which evaluates both individual and consecutive reasoning steps from fine-grained and coarse-grounded level. |
| Outcome: | Empirical results show that the proposed model performs better than existing PRMs and is more robust than existing models. |
Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have advanced mathematical reasoning, but they still struggle with out-of-distribution (OOD) issues. |
| Approach: | They propose a framework to evaluate the logical validity of reasoning steps . they retrieves semantically similar questions and steps for PRM as a warmup . |
| Outcome: | The proposed framework outperforms baseline models on multiple real-world datasets. |
Exploring Generative Process Reward Modeling for Semi-Structured Data: A Case Study of Table Question Answering (2026.eacl-short)
Copied to clipboard
| Challenge: | Recent advances in process reward models (PRMs) have demonstrated remarkable improvements in the reasoning capabilities of large language models (LLMs). |
| Approach: | They evaluate state-of-the-art generative PRMs on table question answering from answer and step perspectives and compare their results to previous studies. |
| Outcome: | The proposed model can aid solution selection but struggle to generalize to out-of-domain data. |
Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly relied upon for solving complex reasoning tasks. |
| Approach: | They propose to use Process Reward Models to scale inference time compute by generating in parallel . they propose to provide early signals that enable the rejection of suboptimal candidates before full generation of step is complete. |
| Outcome: | The proposed method achieves 1.4 – 9 reduction in inference FLOPs without degrading final performance. |