# ScRPO: From Errors to Insights

arXiv: https://arxiv.org/abs/2511.06065 · HTML: https://mlsanity.com/paper/2511.06065/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 8 Nov 2025.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [Learning From Mistakes Makes LLM Better Reasoner](https://mlsanity.com/paper/2310.20689/) (2023)
- [Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate](https://mlsanity.com/paper/2501.17703/) (2025)
- [Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search](https://mlsanity.com/paper/2502.02508/) (2025)
- [AI Flow at the Network Edge](https://mlsanity.com/paper/2411.12469/) (2024)
- [AI Flow: Perspectives, Scenarios, and Approaches](https://mlsanity.com/paper/2506.12479/) (2025)
- [RLVR-World: Training World Models with Reinforcement Learning](https://mlsanity.com/paper/2505.13934/) (2025)
- [Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning](https://mlsanity.com/paper/2502.06533/) (2025)
- [Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.24726/) (2025)
- [Hybrid Group Relative Policy Optimization: A Multi-Sample Approach to Enhancing Policy Optimization](https://mlsanity.com/paper/2502.01652/) (2025)
- [Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling](https://mlsanity.com/paper/2509.25361/) (2025)
- [Advancing Multi-Step Mathematical Reasoning in Large Language Models through Multi-Layered Self-Reflection with Auto-Prompting](https://mlsanity.com/paper/2506.23888/) (2025)

## Built on by (most cited first, 1 of 1)

- [Skip-Connected Policy Optimization for Implicit Advantage](https://mlsanity.com/paper/2604.08690/) (2026)

## Abstract (arXiv)

We introduce Self-correction Relative Policy Optimization (ScRPO), a novel reinforcement learning framework designed to empower large language models with advanced mathematical reasoning capabilities through iterative self-reflection and error correction. The ScRPO framework operates in two distinct phases: (1) Trial-and-error learning stage, where the model is trained via GRPO, and incorrect responses are collected to form an "error pool"; and (2) Self-correction learning stage, which guides the model to introspectively analyze and rectify the reasoning flaws behind its previous errors. Extensive evaluations across challenging mathematical benchmarks, including AIME, AMC, Olympiad, MATH-500, and GSM8k, validate the efficacy of our approach. Using DeepSeek-R1-Distill-Qwen-1.5B and 7B as backbones, ScRPO achieves average accuracies of 64.8% and 77.8%, respectively. This represents a significant improvement of 6.0% and 3.2% over vanilla baselines, consistently outperforming strong post-training methods such as DAPO and GRPO. These findings establish ScRPO as a robust paradigm for enabling autonomous self-improvement in AI systems, particularly in tasks with limited external feedback.