# R-PRM: Reasoning-Driven Process Reward Modeling

arXiv: https://arxiv.org/abs/2503.21295 · HTML: https://mlsanity.com/paper/2503.21295/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 19 of 19)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [MathScale: Scaling Instruction Tuning for Mathematical Reasoning](https://mlsanity.com/paper/2403.02884/) (2024)
- [PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models](https://mlsanity.com/paper/2501.03124/) (2025)
- [Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision](https://mlsanity.com/paper/2403.09472/) (2024)
- [Process-based Self-Rewarding Language Models](https://mlsanity.com/paper/2503.03746/) (2025)

## Built on by (most cited first, 30 of 38)

- [A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models](https://mlsanity.com/paper/2510.08049/) (2025)
- [What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning](https://mlsanity.com/paper/2505.22148/) (2025)
- [RAFFLES: Reasoning-based Attribution of Faults for LLM Systems](https://mlsanity.com/paper/2509.06822/) (2025)
- [Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards](https://mlsanity.com/paper/2505.02686/) (2025)
- [GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning](https://mlsanity.com/paper/2508.04088/) (2025)
- [Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning](https://mlsanity.com/paper/2509.26578/) (2025)
- [Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner](https://mlsanity.com/paper/2507.23317/) (2025)
- [HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMs](https://mlsanity.com/paper/2511.18760/) (2025)
- [Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision](https://mlsanity.com/paper/2505.19706/) (2025)
- [Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey](https://mlsanity.com/paper/2510.01925/) (2025)
- [Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation](https://mlsanity.com/paper/2602.09305/) (2026)
- [DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment](https://mlsanity.com/paper/2605.03327/) (2026)
- [PATS: Process-Level Adaptive Thinking Mode Switching](https://mlsanity.com/paper/2505.19250/) (2025)
- [StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models](https://mlsanity.com/paper/2508.05383/) (2025)
- [SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning](https://mlsanity.com/paper/2509.16548/) (2025)
- [SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration](https://mlsanity.com/paper/2605.14089/) (2026)
- [Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification](https://mlsanity.com/paper/2601.22642/) (2026)
- [Characterizing, Evaluating, and Optimizing Complex Reasoning](https://mlsanity.com/paper/2602.08498/) (2026)
- [SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling](https://mlsanity.com/paper/2506.15498/) (2025)
- [ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling](https://mlsanity.com/paper/2510.14703/) (2025)
- [OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification](https://mlsanity.com/paper/2512.10756/) (2025)
- [Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models](https://mlsanity.com/paper/2603.16253/) (2026)
- [SDR: Set-Distance Rewards for Radiology Report Generation](https://mlsanity.com/paper/2606.00440/) (2026)
- [AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models](https://mlsanity.com/paper/2508.06124/) (2025)
- [Exploring Generative Process Reward Modeling for Semi-Structured Data: A Case Study of Table Question Answering](https://mlsanity.com/paper/2510.20304/) (2025)
- [Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations](https://mlsanity.com/paper/2603.17305/) (2026)
- [Pause or Fabricate? Training Language Models for Grounded Reasoning](https://mlsanity.com/paper/2604.19656/) (2026)
- [From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding](https://mlsanity.com/paper/2605.15951/) (2026)
- [Process Supervision via Verbal Critique Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2604.21611/) (2026)
- [VeriBound: PAC-Bayesian Generalization Bounds for Process Reward Models Trained with Formal Verification Tools](https://mlsanity.com/paper/2606.20740/) (2026)

## Abstract (arXiv)

Large language models (LLMs) inevitably make mistakes when performing step-by-step mathematical reasoning. Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step. However, existing PRMs typically output evaluation scores directly, limiting both learning efficiency and evaluation accuracy, which is further exacerbated by the scarcity of annotated data. To address these issues, we propose Reasoning-Driven Process Reward Modeling (R-PRM). First, we leverage stronger LLMs to generate seed data from limited annotations, effectively bootstrapping our model's reasoning capabilities and enabling comprehensive step-by-step evaluation. Second, we further enhance performance through preference optimization, without requiring additional annotated data. Third, we introduce inference-time scaling to fully harness the model's reasoning potential. Extensive experiments demonstrate R-PRM's effectiveness: on ProcessBench and PRMBench, it surpasses strong baselines by 11.9 and 8.5 points in F1 scores, respectively. When applied to guide mathematical reasoning, R-PRM achieves consistent accuracy improvements of over 8.5 points across six challenging datasets. Further analysis reveals that R-PRM exhibits more comprehensive evaluation and stronger generalization capabilities, thereby highlighting its significant potential.