# RePO: Replay-Enhanced Policy Optimization

arXiv: https://arxiv.org/abs/2506.09340 · HTML: https://mlsanity.com/paper/2506.09340/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [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)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild](https://mlsanity.com/paper/2503.18892/) (2025)
- [Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model](https://mlsanity.com/paper/2503.24290/) (2025)
- [Learning to Reason under Off-Policy Guidance](https://mlsanity.com/paper/2504.14945/) (2025)
- [DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning](https://mlsanity.com/paper/2504.11456/) (2025)
- [Teaching Large Language Models to Reason with Reinforcement Learning](https://mlsanity.com/paper/2403.04642/) (2024)
- [CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models](https://mlsanity.com/paper/2503.22342/) (2025)
- [Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning](https://mlsanity.com/paper/2504.13818/) (2025)
- [What Makes a Reward Model a Good Teacher? An Optimization Perspective](https://mlsanity.com/paper/2503.15477/) (2025)
- [Vanishing Gradients in Reinforcement Finetuning of Language Models](https://mlsanity.com/paper/2310.20703/) (2023)

## Built on by (most cited first, 30 of 39)

- [Geometric-Mean Policy Optimization](https://mlsanity.com/paper/2507.20673/) (2025)
- [ExGRPO: Learning to Reason from Experience](https://mlsanity.com/paper/2510.02245/) (2025)
- [MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems](https://mlsanity.com/paper/2509.22047/) (2025)
- [Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic](https://mlsanity.com/paper/2603.01162/) (2026)
- [XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation](https://mlsanity.com/paper/2510.06672/) (2025)
- [Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model](https://mlsanity.com/paper/2507.06892/) (2025)
- [AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video](https://mlsanity.com/paper/2508.03100/) (2025)
- [AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning](https://mlsanity.com/paper/2512.13278/) (2025)
- [Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning](https://mlsanity.com/paper/2602.01058/) (2026)
- [Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model](https://mlsanity.com/paper/2603.25184/) (2026)
- [Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization](https://mlsanity.com/paper/2511.20718/) (2025)
- [Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding](https://mlsanity.com/paper/2604.26779/) (2026)
- [RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning](https://mlsanity.com/paper/2606.01281/) (2026)
- [Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning](https://mlsanity.com/paper/2602.20722/) (2026)
- [OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models](https://mlsanity.com/paper/2604.04142/) (2026)
- [Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning](https://mlsanity.com/paper/2604.07941/) (2026)
- [PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning](https://mlsanity.com/paper/2508.21104/) (2025)
- [DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay](https://mlsanity.com/paper/2603.16157/) (2026)
- [Find, Fix, Reason: Context Repair for Video Reasoning](https://mlsanity.com/paper/2604.16243/) (2026)
- [Learning from the Near Future: Temporal Self-Distillation for RLVR](https://mlsanity.com/paper/2604.20733/) (2026)
- [Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning](https://mlsanity.com/paper/2604.28005/) (2026)
- [Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients](https://mlsanity.com/paper/2606.18216/) (2026)
- [From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs](https://mlsanity.com/paper/2510.05169/) (2025)
- [Rollout-Level Advantage-Prioritized Experience Replay for GRPO](https://mlsanity.com/paper/2606.04560/) (2026)
- [Experience Augmented Policy Optimization for LLM Reasoning](https://mlsanity.com/paper/2606.30420/) (2026)
- [Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies](https://mlsanity.com/paper/2508.03194/) (2025)
- [One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry](https://mlsanity.com/paper/2601.22521/) (2026)
- [Decoding in Geometry: Alleviating Embedding-Space Crowding for Complex Reasoning](https://mlsanity.com/paper/2601.22536/) (2026)
- [PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning](https://mlsanity.com/paper/2602.03190/) (2026)
- [Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR](https://mlsanity.com/paper/2602.12642/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy outputs per prompt, leading to high computational costs and low data efficiency. To address this, we introduce Replay-Enhanced Policy Optimization (RePO), which leverages diverse replay strategies to retrieve off-policy samples from a replay buffer, allowing policy optimization based on a broader and more diverse set of samples for each prompt. Experiments on five LLMs across seven mathematical reasoning benchmarks demonstrate that RePO achieves absolute average performance gains of 18.4 and 4.1 points for Qwen2.5-Math-1.5B and Qwen3-1.7B, respectively, compared to GRPO. Further analysis indicates that RePO increases computational cost by 15% while raising the number of effective optimization steps by 48% for Qwen3-1.7B, with both on-policy and off-policy sample numbers set to 8. The repository can be accessed at https://github.com/SihengLi99/RePO.