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

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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations