# Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner

arXiv: https://arxiv.org/abs/2507.23317 · HTML: https://mlsanity.com/paper/2507.23317/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 48 of its 65 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 30 of 48)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [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)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model](https://mlsanity.com/paper/2503.24290/) (2025)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [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)
- [Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning](https://mlsanity.com/paper/2410.08146/) (2024)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs](https://mlsanity.com/paper/2501.18585/) (2025)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [Generative Reward Models](https://mlsanity.com/paper/2410.12832/) (2024)
- [Process Reward Models That Think](https://mlsanity.com/paper/2504.16828/) (2025)
- [Critique-out-Loud Reward Models](https://mlsanity.com/paper/2408.11791/) (2024)
- [PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models](https://mlsanity.com/paper/2501.03124/) (2025)
- [GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning](https://mlsanity.com/paper/2504.00891/) (2025)
- [OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models](https://mlsanity.com/paper/2410.09671/) (2024)
- [Process Reward Model with Q-Value Rankings](https://mlsanity.com/paper/2410.11287/) (2024)

## Built on by (most cited first, 11 of 11)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models](https://mlsanity.com/paper/2510.08049/) (2025)
- [StepWiser: Stepwise Generative Judges for Wiser Reasoning](https://mlsanity.com/paper/2508.19229/) (2025)
- [Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models](https://mlsanity.com/paper/2509.26628/) (2025)
- [Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought](https://mlsanity.com/paper/2510.04230/) (2025)
- [PRInTS: Reward Modeling for Long-Horizon Information Seeking](https://mlsanity.com/paper/2511.19314/) (2025)
- [Verifying Meta-Awareness via Predictive Rewards in Reasoning Models](https://mlsanity.com/paper/2510.03259/) (2025)
- [LLM Reasoning with Process Rewards for Outcome-Guided Steps](https://mlsanity.com/paper/2604.02341/) (2026)
- [Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning](https://mlsanity.com/paper/2603.18533/) (2026)
- [BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation](https://mlsanity.com/paper/2606.15893/) (2026)
- [Rewarding Better Thinking for LLM Preference Alignment](https://mlsanity.com/paper/2607.19824/) (2026)

## Abstract (arXiv)

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in inefficient optimization process. In this work, we investigate the function of process reward models (PRMs) to accelerate the RL training for LRMs. We propose a novel intrinsic signal-driven generative process evaluation mechanism operating at the thought level to address major bottlenecks in RL-based training. Specifically, instead of requiring PRMs to know how to solve problems, our method uses intrinsic signals in solutions to judge stepwise correctness and aggregate contiguous correct/incorrect steps into coherent 'thought' units. This structured, thought-level rewards enable more reliable credit assignment by reducing ambiguity in step segmentation and alleviating reward hacking. We further introduce a capability-adaptive reward mechanism that dynamically balances exploration and exploitation based on the LRM's current proficiency, guiding learning without stifling creative trial-and-error. These innovations are integrated into a new off-policy RL algorithm, TP-GRPO, which extends grouped proximal optimization with process-based rewards and improves training efficiency. Experiments on 1.5B and 7B parameter LRMs demonstrate that our method achieves higher problem-solving accuracy with significantly fewer training samples than outcome-only reward baselines. The results validate that well-structured process rewards can substantially accelerate LRM optimization in math reasoning tasks. Code is available at https://github.com/cs-holder/tp_grpo.